© 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. 125448
    Prev
    Next
    INDEX
    Explanations

    time-related indicators and statistical 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
    ɵ
    -0.07
    //{{
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.07
    ête
    -0.07
    /*č↵
    -0.07
    _nsec
    -0.07
    .visitMethod
    -0.07
    è²Ŀ
    -0.07
    andre
    -0.07
    utting
    -0.07
    POSITIVE LOGITS
     reporting
    0.07
    appers
    0.06
    iger
    0.06
    alf
    0.06
    able
    0.06
     sustained
    0.06
     reports
    0.05
    _reporting
    0.05
     relay
    0.05
    zn
    0.05
    Activations Density 0.000%

    No Known Activations