© 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. 40654
    Prev
    Next
    INDEX
    Explanations

    HTML or coding related elements and attributes

    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
    imdi
    -0.07
    ILED
    -0.07
    گار
    -0.07
    AVING
    -0.07
    .Basic
    -0.07
    å¾Ĵ
    -0.06
    à¸ķ
    -0.06
    .Cast
    -0.06
    aug
    -0.06
    943
    -0.06
    POSITIVE LOGITS
     hidden
    0.14
    hidden
    0.12
     Hidden
    0.11
    -hidden
    0.11
    :hidden
    0.10
     hid
    0.10
    Hidden
    0.10
    _hidden
    0.09
    (hidden
    0.09
    .hidden
    0.09
    Activations Density 0.008%

    No Known Activations