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. 77236
    Prev
    Next
    INDEX
    Explanations

    information related to educational programs and enrollment processes

    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
    мом
    -0.06
    eum
    -0.06
    gram
    -0.06
    ift
    -0.06
    graphics
    -0.06
    ickle
    -0.06
    umni
    -0.06
     Alumni
    -0.05
    urovision
    -0.05
     alumni
    -0.05
    POSITIVE LOGITS
     Status
    0.07
    afa
    0.07
     status
    0.07
     Cou
    0.07
    isen
    0.07
    status
    0.07
    iscal
    0.06
     Hayward
    0.06
    /stdc
    0.06
     Mor
    0.06
    Activations Density 0.007%

    No Known Activations