© 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. 9-LLAMASCOPE-RES-131K
    11. 95664
    Prev
    Next
    INDEX
    Explanations

    mentions of programming or code-related keywords

    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
    inos
    -0.07
    \Service
    -0.07
    _Tis
    -0.07
    stery
    -0.06
    chan
    -0.06
    ofile
    -0.06
    CRET
    -0.06
     Germ
    -0.06
    optera
    -0.06
    ino
    -0.06
    POSITIVE LOGITS
    aison
    0.06
    ubar
    0.06
    ;amp
    0.06
    unar
    0.06
    arga
    0.06
     domin
    0.06
     Tmin
    0.06
    .dashboard
    0.06
    одаÑĢ
    0.06
    soup
    0.06
    Activations Density 0.000%

    No Known Activations