© 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. 94874
    Prev
    Next
    INDEX
    Explanations

    elements related to documenting events, particularly in photography and film

    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
    éĺħ读
    -0.07
    ulumi
    -0.06
     Reading
    -0.06
    removeAttr
    -0.06
    _SAFE
    -0.06
    iad
    -0.06
     reads
    -0.06
     Ms
    -0.06
    Reading
    -0.06
    jal
    -0.06
    POSITIVE LOGITS
     recording
    0.14
     capturing
    0.12
    .capture
    0.12
     recorder
    0.12
    Recording
    0.11
     capture
    0.11
    capture
    0.11
     Recording
    0.10
    Recorder
    0.10
     Capture
    0.10
    Activations Density 0.150%

    No Known Activations