© 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. 77385
    Prev
    Next
    INDEX
    Explanations

    awards and honors bestowed upon individuals

    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
    침
    -0.09
    anoia
    -0.08
    zier
    -0.08
    veau
    -0.08
    ÑĢоÑģÑĤ
    -0.07
    Łèĥ½
    -0.07
    zens
    -0.07
    setStatus
    -0.07
    ë´IJ
    -0.07
    fü
    -0.07
    POSITIVE LOGITS
    0.07
     lifetime
    0.06
     recipients
    0.06
     Inn
    0.06
     recipient
    0.06
     pair
    0.06
     citation
    0.06
     Outstanding
    0.06
     Inline
    0.05
     nomination
    0.05
    Activations Density 0.025%

    No Known Activations