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. 78408
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of choosing and utilizing various resources or strategies

    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
     dán
    -0.10
     hã
    -0.09
    itol
    -0.09
    #af
    -0.08
    ç¤
    -0.08
    çı
    -0.08
     dù
    -0.08
     dikke
    -0.08
     hete
    -0.08
     дÑĢÑĥ
    -0.08
    POSITIVE LOGITS
     the
    0.08
     of
    0.08
     Inc
    0.07
    a
    0.07
    -
    0.06
     Chandler
    0.06
    is
    0.06
    's
    0.06
     a
    0.06
     Wilkinson
    0.06
    Activations Density 0.030%

    No Known Activations