© 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. 125482
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities related to dimensions

    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
    agrant
    -0.07
    lagen
    -0.06
    ixon
    -0.06
    acci
    -0.06
    à¸IJ
    -0.06
    _MASK
    -0.06
    éŀ
    -0.06
     subsidi
    -0.06
    nect
    -0.06
    iscrimination
    -0.06
    POSITIVE LOGITS
     fact
    0.07
     Pit
    0.06
     measuring
    0.06
    ential
    0.06
     facts
    0.06
     Verde
    0.06
    itters
    0.06
     flats
    0.06
     standardized
    0.06
    ãĥ¼ãĥ«
    0.06
    Activations Density 0.000%

    No Known Activations