© 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. 126804
    Prev
    Next
    INDEX
    Explanations

    references to taking steps or actions towards progress or improvement

    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
    ATS
    -0.07
    ongan
    -0.07
    lico
    -0.06
    rego
    -0.06
    pcf
    -0.06
    ndl
    -0.06
    oders
    -0.06
    èo
    -0.06
     bang
    -0.06
    ADI
    -0.06
    POSITIVE LOGITS
    /stdc
    0.08
    (s
    0.07
    vrier
    0.07
    ÑĢоÑģÑĤо
    0.07
    γÏģά
    0.07
    avanaugh
    0.07
    iotic
    0.07
    removed
    0.07
    /oct
    0.06
    sono
    0.06
    Activations Density 0.003%

    No Known Activations