© 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. 77057
    Prev
    Next
    INDEX
    Explanations

    questions or phrases beginning with "Which."

    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
    ationally
    -0.06
    Wunused
    -0.06
    indow
    -0.06
    zym
    -0.06
    anches
    -0.06
    zon
    -0.06
    ropa
    -0.06
    zilla
    -0.06
    adium
    -0.06
    tron
    -0.06
    POSITIVE LOGITS
     Wich
    0.08
    ens
    0.07
    ale
    0.07
    erts
    0.07
    rone
    0.07
    areth
    0.07
    vero
    0.07
     _('
    0.06
    dens
    0.06
    åĢī
    0.06
    Activations Density 0.008%

    No Known Activations