© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42778
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens in the context of commercial lease terminology—e.g. references to lease duration (“multi-year”), lease type (“triple-net”), renewals (“renewed”), and related lease details.

    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
    Latin
    -0.07
     medicinal
    -0.07
     normalized
    -0.06
    normalized
    -0.06
    厚
    -0.06
    posure
    -0.06
    ]()
    -0.06
    攻
    -0.06
     Henri
    -0.06
    сл
    -0.06
    POSITIVE LOGITS
    _SRC
    0.07
     mechanisms
    0.07
    -CP
    0.07
     mechanism
    0.06
    _Search
    0.06
     hint
    0.06
     incomplete
    0.06
    smarty
    0.06
     경제
    0.06
    drFc
    0.06
    Activations Density 0.110%

    No Known Activations