© 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. 16172
    Prev
    Next
    INDEX
    Explanations

    references and links to documentation or APIs

    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
    ãĥ¼ãĤ¸
    -0.07
    avia
    -0.06
    λικ
    -0.06
    iece
    -0.06
    523
    -0.06
    Choice
    -0.06
    .GridView
    -0.06
    peria
    -0.06
     Presented
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     documentation
    0.11
     docs
    0.11
     manual
    0.10
     official
    0.10
     manuals
    0.09
     wiki
    0.09
    documentation
    0.09
    å®ĺç½ij
    0.09
    manual
    0.09
     guide
    0.09
    Activations Density 0.029%

    No Known Activations