© 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. 27321
    Prev
    Next
    INDEX
    Explanations

    references to types or categories of objects

    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
    ry
    -0.11
    ary
    -0.08
    endo
    -0.07
    ri
    -0.07
    Enum
    -0.07
    vation
    -0.07
    aries
    -0.07
    our
    -0.07
     Beg
    -0.07
    rs
    -0.07
    POSITIVE LOGITS
    ahead
    0.13
    face
    0.11
    etting
    0.11
    faces
    0.10
    casting
    0.09
    æħĭ
    0.09
    icals
    0.09
    ICAL
    0.08
     dáng
    0.07
    ologies
    0.07
    Activations Density 0.068%

    No Known Activations