© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109444
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash

    code related to setting up server-client communications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily responds to numeric literal tokens (e.g. standalone numbers, IP address segments, port numbers, and other digit strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bee
    -0.07
    pletion
    -0.07
    attend
    -0.06
     ListBox
    -0.06
     unarmed
    -0.06
    Digital
    -0.06
    acing
    -0.06
    							↵
    -0.06
    ordial
    -0.06
    ilenames
    -0.06
    POSITIVE LOGITS
    .eulerAngles
    0.07
     Roo
    0.07
     synthesis
    0.06
    _PED
    0.06
     transition
    0.06
     musica
    0.06
     Hugo
    0.06
    _logits
    0.06
     �
    0.06
    ugal
    0.06
    Activations Density 0.202%

    No Known Activations