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. 15-RESID-POST-AA
    6. 89093
    Prev
    Next
    INDEX
    Explanations

    Override

    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
     Spider
    -0.07
     contempl
    -0.07
     situated
    -0.07
     fractional
    -0.07
    56
    -0.06
    Cal
    -0.06
    753
    -0.06
    	pos
    -0.06
     ph
    -0.06
    52
    -0.06
    POSITIVE LOGITS
    orraine
    0.07
    _override
    0.07
     overwhelming
    0.07
    ınma
    0.07
    .cloudflare
    0.07
    override
    0.07
     overriding
    0.07
     mode
    0.07
     oversized
    0.06
     Marc
    0.06
    Activations Density 0.008%

    No Known Activations