© 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. 76342
    Prev
    Next
    INDEX
    Explanations

    phrases related to service offerings and technical support

    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
    embr
    -0.07
    kehr
    -0.06
     Kennedy
    -0.06
     demanding
    -0.06
    ainter
    -0.06
    tribute
    -0.06
    lean
    -0.06
    argas
    -0.06
     -----------------------------------------------------------------------------↵
    -0.06
    Orth
    -0.06
    POSITIVE LOGITS
     hang
    0.07
    Hang
    0.07
     anim
    0.07
     Hang
    0.07
    acia
    0.06
    ä¹ĥ
    0.06
     invis
    0.06
    è¡
    0.06
    if
    0.06
    iment
    0.06
    Activations Density 0.032%

    No Known Activations