Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 66016
    Prev
    Next
    INDEX
    Explanations

    mental health

    np_max-act · gemini-2.0-flash

    Text discussing mental health issues (especially depression and suicidal risk) and related help/resources.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    interp
    -0.07
    usters
    -0.07
    IENT
    -0.06
     opera
    -0.06
    .config
    -0.06
     scripture
    -0.06
    Mixed
    -0.06
    chg
    -0.06
     Educ
    -0.06
     Mend
    -0.06
    POSITIVE LOGITS
    官方
    0.07
    _IMAGE
    0.07
     xc
    0.07
     Om
    0.06
     marvelous
    0.06
    <Location
    0.06
     оскільки
    0.06
    .DateFormat
    0.06
    -basic
    0.06
    (savedInstanceState
    0.06
    Activations Density 0.172%

    No Known Activations