© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    into/in

    np_max-act · gemini-2.0-flash

    The neuron flags instances of the verb “go” (and its forms) when it introduces movement into a location (e.g. “go in,” “go into,” “going into”).

    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
     lm
    -0.07
    Lee
    -0.07
     Contribution
    -0.06
    TT
    -0.06
     güçlü
    -0.06
    το
    -0.06
     vine
    -0.06
     let
    -0.06
    _tree
    -0.06
     quella
    -0.06
    POSITIVE LOGITS
     �
    0.07
    __.__
    0.07
     Sabha
    0.07
    (off
    0.07
    .unsqueeze
    0.06
    uracy
    0.06
     Incorrect
    0.06
    ecký
    0.06
    ↵	
↵
    0.06
    ابق
    0.06
    Activations Density 0.035%

    No Known Activations