Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77319
    Prev
    Next
    INDEX
    Explanations

    citations and references related to academic or informational content

    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
    576
    -0.07
    497
    -0.07
    Joined
    -0.06
     Daw
    -0.06
    Caught
    -0.06
    ÑĪев
    -0.06
    olini
    -0.06
    onto
    -0.06
     Old
    -0.06
     Caught
    -0.06
    POSITIVE LOGITS
    .ops
    0.07
    ARB
    0.07
    ĶåĽŀ
    0.07
    uild
    0.07
     via
    0.06
    /TT
    0.06
    iot
    0.06
    ufen
    0.06
    erosis
    0.06
    perimental
    0.06
    Activations Density 0.007%

    No Known Activations