© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94168
    Prev
    Next
    INDEX
    Explanations

    references to bibliotherapy and related terms

    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
    ifa
    -0.07
    rank
    -0.07
    ationToken
    -0.07
    ivas
    -0.07
    ftware
    -0.07
    igm
    -0.07
    _mE
    -0.07
    ÎIJ
    -0.06
    ives
    -0.06
    abil
    -0.06
    POSITIVE LOGITS
    lio
    0.10
    lical
    0.10
    TeX
    0.07
    asset
    0.07
    woke
    0.07
    ulous
    0.06
    uild
    0.06
    utow
    0.06
    urger
    0.06
    iri
    0.06
    Activations Density 0.006%

    No Known Activations