© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 25023
    Prev
    Next
    INDEX
    Explanations

    negative experiences

    np_max-act · gemini-2.0-flash

    statements where the assistant describes its capabilities, limitations, and offers help (self-portrayal as an AI across languages).

    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
    idable
    -0.07
     Singular
    -0.07
    	state
    -0.07
     Biblical
    -0.07
     Saudi
    -0.07
    рел
    -0.07
    _dep
    -0.06
    erson
    -0.06
    Null
    -0.06
     yerel
    -0.06
    POSITIVE LOGITS
     fundra
    0.06
    ้ต
    0.06
     piger
    0.06
    ॉ
    0.06
     QUICK
    0.06
    .concatenate
    0.06
    扣
    0.05
    Entre
    0.05
     novice
    0.05
    urtle
    0.05
    Activations Density 0.784%

    No Known Activations