© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 93133
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the letters "s," "m," and "t," which may indicate a focus on adjectives or action verbs in a context

    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
    c
    -0.12
    a
    -0.12
    s
    -0.12
    i
    -0.11
    b
    -0.11
    d
    -0.11
    m
    -0.10
    y
    -0.10
    p
    -0.10
    r
    -0.10
    POSITIVE LOGITS
    ory
    0.07
    ;element
    0.07
    uteur
    0.07
    /o
    0.06
    ÑĢаÐ
    0.06
    ture
    0.06
    cean
    0.06
    EMA
    0.06
    spacing
    0.06
    atego
    0.06
    Activations Density 0.117%

    No Known Activations