© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13928
    Prev
    Next
    INDEX
    Explanations

    rebuttals or counterarguments

    np_max-act · gemini-2.0-flash

    The neuron activates on longer, evaluative or policy-oriented words that appear in opinionated or analytical contexts (e.g. “speculators,” “concern,” “strengthening,” “engage”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     remodeling
    -0.07
     pepper
    -0.07
     каш
    -0.07
     감사
    -0.06
     ή
    -0.06
    しま
    -0.06
    (ra
    -0.06
     wann
    -0.06
     constructions
    -0.06
    _Lean
    -0.06
    POSITIVE LOGITS
     allocate
    0.07
     Aid
    0.06
    กำ
    0.06
    IALIZED
    0.06
     renting
    0.06
    _BYTES
    0.06
    核
    0.06
    응
    0.06
     //////////////////
    0.06
    _CAP
    0.06
    Activations Density 0.095%

    No Known Activations