© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87680
    Prev
    Next
    INDEX
    Explanations

    URLs and website references

    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
    MLS
    -0.07
    abb
    -0.06
     Laboratories
    -0.06
    eneral
    -0.06
    indows
    -0.06
    ull
    -0.06
    _
    -0.06
    @yahoo
    -0.06
    @gmail
    -0.06
     invade
    -0.06
    POSITIVE LOGITS
    лÑİÑĩа
    0.08
    _Static
    0.08
    ï¼
    0.07
    _PD
    0.07
     paci
    0.07
    jeta
    0.07
     Yuk
    0.07
    www
    0.07
    iras
    0.07
     www
    0.07
    Activations Density 0.021%

    No Known Activations