© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60258
    Prev
    Next
    INDEX
    Explanations

    references to economic factors and conditions influencing consumer behavior

    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
    ɵ
    -0.09
    ftype
    -0.08
    abez
    -0.07
     Stark
    -0.07
    avec
    -0.07
    <?,
    -0.07
    _EXTERN
    -0.07
    缮ãĤĴ
    -0.07
    _skb
    -0.07
    onth
    -0.07
    POSITIVE LOGITS
     growth
    0.07
     reason
    0.07
     trends
    0.06
     reasons
    0.06
    reason
    0.06
     major
    0.06
    ingle
    0.06
     further
    0.06
    posit
    0.06
    Reason
    0.06
    Activations Density 0.003%

    No Known Activations