© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61332
    Prev
    Next
    INDEX
    Explanations

    references to locations and adjacent places

    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
    ochen
    -0.07
     ank
    -0.07
    utos
    -0.07
    imo
    -0.07
     stra
    -0.07
    988
    -0.06
    ifle
    -0.06
    ÑĤÑĢо
    -0.06
    ils
    -0.06
    esthesia
    -0.06
    POSITIVE LOGITS
    /down
    0.08
    /on
    0.08
     neighbors
    0.07
     neighbor
    0.07
    enan
    0.07
    /by
    0.06
    467
    0.06
    /time
    0.06
    /out
    0.06
    rous
    0.06
    Activations Density 0.005%

    No Known Activations