© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61313
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and data reporting, particularly about trends and changes 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
     âĹĦ
    -0.06
     finally
    -0.06
     perhaps
    -0.06
    GLOBALS
    -0.06
    304
    -0.06
    SBATCH
    -0.06
     maybe
    -0.06
    jen
    -0.06
    oce
    -0.06
     ultimately
    -0.06
    POSITIVE LOGITS
    letic
    0.07
    LEM
    0.07
     Tin
    0.06
    ean
    0.06
    _SF
    0.06
    esc
    0.06
    ussy
    0.06
     underst
    0.06
    ghan
    0.06
    versions
    0.06
    Activations Density 0.021%

    No Known Activations