© 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. 57201
    Prev
    Next
    INDEX
    Explanations

    plot elements and narrative concepts in film reviews

    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
    rsp
    -0.07
    lew
    -0.06
    undry
    -0.06
     Sherlock
    -0.06
     indispens
    -0.06
     evidence
    -0.06
     못
    -0.06
    ekler
    -0.06
    loh
    -0.06
    antry
    -0.06
    POSITIVE LOGITS
     premise
    0.10
    idea
    0.08
     premises
    0.08
     Idea
    0.07
     fertile
    0.07
    ä¼ģ
    0.07
    concept
    0.07
    ERGE
    0.07
     idea
    0.07
     concept
    0.07
    Activations Density 0.049%

    No Known Activations