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. 125592
    Prev
    Next
    INDEX
    Explanations

    details related to logistical information and 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
    641
    -0.07
    linky
    -0.07
    jumbotron
    -0.06
    Ĥ¹
    -0.06
    ehler
    -0.06
     liner
    -0.06
    igner
    -0.06
    haled
    -0.06
    arya
    -0.06
    .vertx
    -0.06
    POSITIVE LOGITS
    pert
    0.08
     date
    0.07
    :date
    0.07
    목
    0.07
    -pagination
    0.07
     Bounds
    0.07
     address
    0.06
    ì§ĢìļĶ
    0.06
     dates
    0.06
    DATED
    0.06
    Activations Density 0.009%

    No Known Activations