© 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. 75342
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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
    har
    -0.07
    _CNTL
    -0.06
    ghi
    -0.06
    icari
    -0.06
     Robinson
    -0.06
    .Servlet
    -0.06
    polator
    -0.06
     FAG
    -0.06
    iske
    -0.06
    Ñīин
    -0.06
    POSITIVE LOGITS
    zelf
    0.08
    å£°éŁ³
    0.07
    áj
    0.07
    491
    0.07
    ing
    0.07
    ermo
    0.07
    ROID
    0.07
    rish
    0.06
    uger
    0.06
    à¯į
    0.06
    Activations Density 0.072%

    No Known Activations