© 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. 15-RESID-POST-AA
    11. 103669
    Prev
    Next
    INDEX
    Explanations

    resignations and refusals

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đời
    -0.06
    Sarah
    -0.06
    (so
    -0.06
    脸
    -0.06
     expres
    -0.06
     voted
    -0.06
     niece
    -0.06
    AX
    -0.06
    speed
    -0.06
     MSS
    -0.06
    POSITIVE LOGITS
     opens
    0.07
     Potential
    0.07
    setState
    0.07
    setPosition
    0.07
    .open
    0.06
    идент
    0.06
     제공
    0.06
     UIStoryboardSegue
    0.06
     estaba
    0.06
     baptism
    0.06
    Activations Density 0.051%

    No Known Activations