© 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. 113446
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    first-person narrative content—self-referential, conversational statements about the speaker’s actions, experiences, plans, or requests in forum-style posts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ance
    -0.08
     gegen
    -0.07
    希
    -0.06
     Belediyesi
    -0.06
    }\.[
    -0.06
    ражд
    -0.06
    _launch
    -0.06
    895
    -0.06
    ?)
    -0.06
     disqualified
    -0.06
    POSITIVE LOGITS
     inj
    0.07
     PRI
    0.06
     hut
    0.06
     firefight
    0.06
    redux
    0.06
     plano
    0.06
     thứ
    0.06
     Θεσσα
    0.06
     MENU
    0.06
     whatsoever
    0.06
    Activations Density 0.080%

    No Known Activations