© 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. 83066
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structure within the text

    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
    ãģİ
    -0.07
    \$
    -0.07
    eller
    -0.07
    asmus
    -0.07
    atham
    -0.06
    ylland
    -0.06
    borg
    -0.06
    (rawValue
    -0.06
    ::-
    -0.06
    ãģĺãĤĥ
    -0.06
    POSITIVE LOGITS
    olik
    0.07
     caption
    0.06
    caption
    0.06
    èĥľ
    0.06
    label
    0.06
     Caption
    0.06
    -caption
    0.06
     ÑĢеÑĩ
    0.06
    'label
    0.06
    ainted
    0.06
    Activations Density 0.030%

    No Known Activations