© 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. 76789
    Prev
    Next
    INDEX
    Explanations

    ampersands in 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
    ses
    -0.14
    /her
    -0.09
    ?s
    -0.08
    ssc
    -0.07
    nt
    -0.07
    ’t
    -0.07
    ese
    -0.07
    ↵
    -0.07
    ÂŃs
    -0.07
    %E
    -0.07
    POSITIVE LOGITS
    amp
    0.29
    nbsp
    0.20
    raquo
    0.17
    AMP
    0.17
    quot
    0.17
    ÑĶм
    0.16
    ï¸ı
    0.14
    apos
    0.13
    emsp
    0.13
     amp
    0.12
    Activations Density 0.062%

    No Known Activations