© 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. 108440
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the intensity or frequency of certain phenomena

    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
     also
    -0.09
    also
    -0.08
    Also
    -0.08
     Also
    -0.07
     ALSO
    -0.07
     actually
    -0.07
     equally
    -0.07
    ä¹Ł
    -0.07
    inqu
    -0.07
     anche
    -0.07
    POSITIVE LOGITS
     today
    0.08
     lately
    0.08
     finally
    0.08
    kur
    0.07
     Finally
    0.07
     among
    0.06
     divisible
    0.06
    undle
    0.06
    finally
    0.06
    νÏĮ
    0.06
    Activations Density 0.080%

    No Known Activations