© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83305
    Prev
    Next
    INDEX
    Explanations

    criticisms and discussions related to arguments or claims

    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
    çµ
    -0.07
    ledi
    -0.07
    anka
    -0.07
    ĨĴ
    -0.07
    annon
    -0.07
    arkan
    -0.07
    asons
    -0.06
    emble
    -0.06
    alf
    -0.06
    arefa
    -0.06
    POSITIVE LOGITS
     part
    0.08
     statement
    0.07
     suggested
    0.07
     Dip
    0.07
     reference
    0.07
     item
    0.07
     included
    0.06
     section
    0.06
     mention
    0.06
     claims
    0.06
    Activations Density 0.054%

    No Known Activations