Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 130241
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    The neuron is triggered by structured‐data field or attribute names (e.g. HTTP header names or XML/JSON property keys).

    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
     tarde
    -0.08
     Rico
    -0.07
    nému
    -0.06
    �
    -0.06
     +(
    -0.06
    	sm
    -0.06
    tube
    -0.06
     Serialize
    -0.06
    .Field
    -0.06
    áře
    -0.06
    POSITIVE LOGITS
    HostName
    0.06
    _NAMES
    0.06
     foundations
    0.06
    aille
    0.06
    Cl
    0.06
     spokesperson
    0.06
     incidents
    0.06
    Tue
    0.06
     Bellev
    0.06
    .openapi
    0.05
    Activations Density 0.009%

    No Known Activations