© 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. 72373
    Prev
    Next
    INDEX
    Explanations

    specific URLs or links related to websites and resources

    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
    enty
    -0.06
    amas
    -0.06
    ffen
    -0.06
     reprodu
    -0.06
    log
    -0.06
    971
    -0.05
    WN
    -0.05
    emer
    -0.05
    ence
    -0.05
    елÑİ
    -0.05
    POSITIVE LOGITS
    usercontent
    0.09
    èķī
    0.08
    ATO
    0.08
    PED
    0.07
    UGIN
    0.07
    IFORM
    0.07
    _ke
    0.07
    ATUS
    0.07
    -lfs
    0.07
    igin
    0.07
    Activations Density 0.002%

    No Known Activations