© 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 EvalsExportsAPI 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. 61096
    Prev
    Next
    INDEX
    Explanations

    references to all-time rankings or records in various contexts

    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
    ãĥĭãĥĥãĤ¯
    -0.07
    utow
    -0.07
    830
    -0.07
    اپ
    -0.06
    abor
    -0.06
    hey
    -0.06
    Ì
    -0.06
    lok
    -0.06
    eren
    -0.06
    assel
    -0.06
    POSITIVE LOGITS
    edly
    0.10
    azar
    0.08
    INLINE
    0.08
    cil
    0.07
    -present
    0.07
    /single
    0.07
    /down
    0.07
    igator
    0.07
    istrate
    0.06
    green
    0.06
    Activations Density 0.002%

    No Known Activations