© 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. 94241
    Prev
    Next
    INDEX
    Explanations

    references to plans and strategies

    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
    olley
    -0.07
    .gdx
    -0.07
    uess
    -0.07
    peare
    -0.06
     RaycastHit
    -0.06
    /antlr
    -0.06
    .ease
    -0.06
    464
    -0.06
    mtime
    -0.06
    kaar
    -0.06
    POSITIVE LOGITS
     plan
    0.27
     plans
    0.25
    plan
    0.21
     Plans
    0.21
    -plan
    0.20
     Plan
    0.20
    Plan
    0.19
    plans
    0.19
    计åĪĴ
    0.18
    _plan
    0.18
    Activations Density 0.152%

    No Known Activations