© 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. 92161
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    the presence of scheduled times or dates in a message.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects email header metadata fields (e.g. “From:”, “Sent:”, “To:”, “Subject:”).

    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
     herself
    -0.07
    lication
    -0.06
     Pl
    -0.06
     nationalists
    -0.06
    .rule
    -0.06
    -caption
    -0.06
    ůž
    -0.06
    (parts
    -0.06
    MIT
    -0.06
     himself
    -0.06
    POSITIVE LOGITS
    ovalo
    0.07
     omega
    0.07
    jít
    0.07
     extingu
    0.07
    +='<
    0.07
     foreach
    0.06
    <class
    0.06
    >If
    0.06
     Dtype
    0.06
    pageIndex
    0.06
    Activations Density 0.003%

    No Known Activations