© 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. 108541
    Prev
    Next
    INDEX
    Explanations

    expressions of personal effort and expectations

    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
    latlong
    -0.07
    lew
    -0.06
    opi
    -0.06
    882
    -0.06
    rane
    -0.06
    ernet
    -0.06
     OpCode
    -0.06
    à¤Ĥà¤ľà¤¨
    -0.06
    inq
    -0.06
    'field
    -0.06
    POSITIVE LOGITS
     nor
    0.08
    save
    0.07
    apan
    0.07
     save
    0.07
    AAC
    0.07
    sal
    0.07
    Nor
    0.07
    assing
    0.06
     Save
    0.06
    lý
    0.06
    Activations Density 0.035%

    No Known Activations