© 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. 9-LLAMASCOPE-RES-131K
    11. 95564
    Prev
    Next
    INDEX
    Explanations

    references to measurements, particularly related to height and depth

    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
    otec
    -0.08
    omanip
    -0.07
    ibox
    -0.07
    upiter
    -0.07
    Ñıж
    -0.06
    ionate
    -0.06
    omens
    -0.06
     boz
    -0.06
    gota
    -0.06
    à¹ģà¸ľ
    -0.06
    POSITIVE LOGITS
    atsby
    0.06
    yer
    0.06
     height
    0.06
    ord
    0.06
     Bart
    0.06
     bindActionCreators
    0.06
    untu
    0.06
     jist
    0.06
    /platform
    0.05
    à¹ģà¸ģ
    0.05
    Activations Density 0.011%

    No Known Activations