© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 129888
    Prev
    Next
    INDEX
    Explanations

    Spanish gerund endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mpeg
    -0.06
    .getList
    -0.06
     якій
    -0.06
    อะไร
    -0.06
     hâl
    -0.06
    iator
    -0.06
    _Rel
    -0.06
    �
    -0.06
    -validator
    -0.06
     Những
    -0.06
    POSITIVE LOGITS
    ando
    0.13
     haciendo
    0.09
    endo
    0.08
     usando
    0.08
    iendo
    0.08
     Quando
    0.08
     dando
    0.08
    mando
    0.08
    ывая
    0.07
    ADO
    0.07
    Activations Density 0.028%

    No Known Activations