© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77401
    Prev
    Next
    INDEX
    Explanations

    phrases related to targeting specific audiences or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _fwd
    -0.06
    fern
    -0.06
    ocha
    -0.06
    ĵ¨
    -0.06
     thread
    -0.06
    ech
    -0.06
    createElement
    -0.06
     requis
    -0.05
    eel
    -0.05
    ire
    -0.05
    POSITIVE LOGITS
    /target
    0.10
    _specific
    0.09
    areas
    0.09
     specific
    0.08
     targets
    0.08
     Specific
    0.07
    .scalablytyped
    0.07
    specific
    0.07
    unsch
    0.07
     ương
    0.07
    Activations Density 0.015%

    No Known Activations