© 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. 61305
    Prev
    Next
    INDEX
    Explanations

    nouns and extravagant features related to luxury experiences and amenities

    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
    å¯
    -0.06
     aver
    -0.06
    æľ
    -0.06
     alleg
    -0.06
    åī
    -0.06
    _approx
    -0.05
     aggreg
    -0.05
    pered
    -0.05
    _expiry
    -0.05
     composition
    -0.05
    POSITIVE LOGITS
    ovit
    0.08
    ULLET
    0.07
    andbox
    0.07
     Gins
    0.07
     resident
    0.07
    onium
    0.07
    urr
    0.07
    hiba
    0.07
    ulfill
    0.06
    hang
    0.06
    Activations Density 0.040%

    No Known Activations