© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6859
    Prev
    Next
    INDEX
    Explanations

    because

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on the causal conjunction “because,” essentially detecting that specific discourse marker.

    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
     any
    -0.06
    inq
    -0.06
    mode
    -0.06
    _VALUES
    -0.06
     tinder
    -0.06
    NdEx
    -0.06
     *__
    -0.06
    [at
    -0.06
     Beste
    -0.06
    .GetInt
    -0.06
    POSITIVE LOGITS
     because
    0.10
     porque
    0.08
     perché
    0.08
     afterwards
    0.08
     Horn
    0.07
    because
    0.07
    ��
    0.07
     guitarist
    0.07
     cui
    0.07
    _builder
    0.07
    Activations Density 0.025%

    No Known Activations