© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29569
    Prev
    Next
    INDEX
    Explanations

    references to numerical statistics or performance metrics in sports 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
    aoke
    -0.08
    รส
    -0.07
    CGSize
    -0.07
    esen
    -0.07
    xia
    -0.07
    ĵåIJį
    -0.07
    .ManyToMany
    -0.07
    Ĺi
    -0.07
    اÙĨÙĬØ©
    -0.06
    urre
    -0.06
    POSITIVE LOGITS
     allo
    0.06
    -NLS
    0.06
    ãĥĥãĥĹ
    0.06
     visiting
    0.06
     delegation
    0.06
    hoo
    0.05
     egg
    0.05
     scr
    0.05
     surpr
    0.05
     Ho
    0.05
    Activations Density 0.027%

    No Known Activations