© 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. 55766
    Prev
    Next
    INDEX
    Explanations

    measurements of dimensions, particularly length and width

    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
    olet
    -0.07
     è±
    -0.07
    istr
    -0.07
    isy
    -0.07
    oust
    -0.07
    quential
    -0.07
    geç
    -0.07
    idth
    -0.07
    å±
    -0.07
    anton
    -0.07
    POSITIVE LOGITS
    LOPT
    0.06
    ouncer
    0.06
    RESSED
    0.06
    بÛĮر
    0.06
    ressed
    0.06
    okit
    0.06
    ness
    0.05
     each
    0.05
     Mon
    0.05
     Moder
    0.05
    Activations Density 0.009%

    No Known Activations