© 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. 74914
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness or readiness to assist and provide information

    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
    ANNEL
    -0.07
    cerr
    -0.06
    urette
    -0.06
    одÑĥ
    -0.06
     Bowman
    -0.06
     Carn
    -0.06
     Reyes
    -0.05
    enville
    -0.05
    ilogy
    -0.05
    Eu
    -0.05
    POSITIVE LOGITS
     any
    0.13
     if
    0.13
     anyone
    0.13
     anybody
    0.12
     qualquer
    0.11
     ANY
    0.11
     cualquier
    0.10
    any
    0.10
    ä»»ä½ķ
    0.10
    (any
    0.10
    Activations Density 0.064%

    No Known Activations