© 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. 78190
    Prev
    Next
    INDEX
    Explanations

    technical specifications and ratings related to media content

    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
     Spo
    -0.08
    OfClass
    -0.07
    zag
    -0.07
    emoc
    -0.07
     Performing
    -0.07
    usercontent
    -0.07
    edic
    -0.07
     retali
    -0.07
    $MESS
    -0.07
    sak
    -0.07
    POSITIVE LOGITS
     director
    0.06
    833
    0.06
    ابة
    0.06
    ëĥIJ
    0.06
     |
    0.06
    53
    0.06
    ç±³
    0.06
     distributor
    0.06
    elman
    0.06
    миÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations