© 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. 40252
    Prev
    Next
    INDEX
    Explanations

    metrics related to physical properties and changes in various scientific 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
    å±Ģ
    -0.07
    olicy
    -0.07
    .metamodel
    -0.06
    ÑĤÑİ
    -0.06
    gado
    -0.06
    xing
    -0.06
    _SL
    -0.06
    ounded
    -0.06
    .OP
    -0.06
    ombine
    -0.06
    POSITIVE LOGITS
     of
    0.06
     extent
    0.06
    ames
    0.06
    çİĦ
    0.06
    ìĬµ
    0.06
    zahl
    0.06
    HER
    0.06
     MES
    0.06
     Aad
    0.06
    urb
    0.06
    Activations Density 0.067%

    No Known Activations