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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27182
    Prev
    Next
    INDEX
    Explanations

    improving products/processes

    np_max-act · gemini-2.0-flash

    The neuron activates on key terms and phrases used to outline the stages of a persuasive copywriting framework (Attention, Interest, Desire, Action).

    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
    งอย
    -0.07
    Strength
    -0.06
     geen
    -0.06
    _Arg
    -0.06
    solver
    -0.06
    916
    -0.06
     Compile
    -0.06
    align
    -0.06
    หาร
    -0.06
     sk
    -0.06
    POSITIVE LOGITS
    NSUserDefaults
    0.06
    definitions
    0.06
    üsseldorf
    0.06
     Rolls
    0.06
    .removeItem
    0.06
    èles
    0.06
     enthus
    0.06
    /network
    0.06
    งน
    0.05
     застосування
    0.05
    Activations Density 0.378%

    No Known Activations