© 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. 90952
    Prev
    Next
    INDEX
    Explanations

    ger/ter

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the letter sequence “mer” embedded within tokens.

    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
    loop
    -0.08
    aku
    -0.08
    xA
    -0.08
     Rainbow
    -0.08
    apo
    -0.08
    onta
    -0.08
    oki
    -0.08
    upa
    -0.08
    anta
    -0.08
    oop
    -0.08
    POSITIVE LOGITS
    er
    0.13
    ER
    0.12
    TER
    0.10
    ter
    0.09
     Ver
    0.09
    _ver
    0.09
    ers
    0.09
     er
    0.09
    HER
    0.09
     Her
    0.09
    Activations Density 0.070%

    No Known Activations