© 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. 56309
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional affiliations

    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
    ãĤħ
    -0.06
    aggi
    -0.06
    oner
    -0.06
    OrDefault
    -0.06
    orton
    -0.06
    adiens
    -0.06
    ibar
    -0.06
    lush
    -0.06
    arin
    -0.06
    izophren
    -0.06
    POSITIVE LOGITS
     Ark
    0.07
    PPER
    0.07
    mailto
    0.07
    ubbles
    0.06
    972
    0.06
     неÑĢ
    0.06
    ायर
    0.06
    952
    0.06
    +'&
    0.06
    950
    0.06
    Activations Density 0.001%

    No Known Activations