© 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. 76710
    Prev
    Next
    INDEX
    Explanations

    references to remnants or survivors of historical or cultural significance

    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
    resse
    -0.07
    arak
    -0.06
    ab
    -0.06
    ÑĸÑĤ
    -0.06
    oa
    -0.06
    ubu
    -0.06
    andy
    -0.06
    agg
    -0.06
     Tomb
    -0.06
    aub
    -0.06
    POSITIVE LOGITS
     remaining
    0.11
    remaining
    0.09
     remnants
    0.09
     Remaining
    0.09
    Remaining
    0.09
     vest
    0.09
    _remaining
    0.08
     intact
    0.08
     original
    0.08
     originals
    0.07
    Activations Density 0.016%

    No Known Activations