© 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. 119174
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating numbered references or citations

    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
    etz
    -0.07
    æĵį
    -0.07
    apore
    -0.07
    rech
    -0.06
    OLOR
    -0.06
    umont
    -0.06
    iddi
    -0.06
    Clr
    -0.06
    iff
    -0.06
    scratch
    -0.06
    POSITIVE LOGITS
    avras
    0.07
    659
    0.06
    EOF
    0.06
     jaz
    0.06
    689
    0.06
    Plus
    0.06
    olk
    0.06
    linkplain
    0.06
    Poll
    0.06
    cales
    0.06
    Activations Density 0.000%

    No Known Activations