© 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. 93979
    Prev
    Next
    INDEX
    Explanations

    sections that contain technical remarks or documentation

    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
    ert
    -0.06
    ront
    -0.06
     Platt
    -0.06
     Realty
    -0.06
    .TabIndex
    -0.05
    лоб
    -0.05
    ents
    -0.05
    .requests
    -0.05
    otre
    -0.05
    hab
    -0.05
    POSITIVE LOGITS
    329
    0.07
    orama
    0.07
    ictim
    0.07
    _ctor
    0.07
    ngör
    0.07
    ystack
    0.07
    ypi
    0.07
    /browse
    0.07
    STACK
    0.06
    INDER
    0.06
    Activations Density 0.006%

    No Known Activations