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. 7-RESID-POST-AA
    6. 26583
    Prev
    Next
    INDEX
    Explanations

    personality traits

    np_max-act · gemini-2.0-flash

    Tokens related to interpersonal emotional states and evaluations (being belittled, trustworthiness, feelings/worries, and similar social-emotional words).

    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_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
     turbulence
    -0.07
     serde
    -0.07
    amon
    -0.07
                  
    -0.07
    Invariant
    -0.07
     });
    ↵
    ↵
    -0.06
    yang
    -0.06
     ard
    -0.06
    Blog
    -0.06
    igen
    -0.06
    POSITIVE LOGITS
    -navigation
    0.07
     Ago
    0.07
     pnl
    0.06
    (front
    0.06
    ντ
    0.06
     typu
    0.06
    �
    0.06
    -ps
    0.05
     :";↵
    0.05
     nejvyšší
    0.05
    Activations Density 0.330%

    No Known Activations