© 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. 15-LLAMASCOPE-RES-131K
    11. 27074
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that describe quality or aesthetics

    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
    ette
    -0.06
    anders
    -0.06
     mili
    -0.06
    orgia
    -0.06
    Ø¡
    -0.06
    vero
    -0.06
     vra
    -0.05
     spirit
    -0.05
    agy
    -0.05
    lia
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    uhn
    0.07
    FindObject
    0.07
    祥
    0.07
    azu
    0.07
    INGER
    0.07
    kehr
    0.07
    æķ¬
    0.06
    (er
    0.06
    infeld
    0.06
    Activations Density 0.014%

    No Known Activations