© 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. 61928
    Prev
    Next
    INDEX
    Explanations

    terms related to alcoholic beverages and their characteristics

    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
     Cannes
    -0.06
    chor
    -0.06
     Battles
    -0.06
    446
    -0.06
    omor
    -0.06
    rani
    -0.05
     Brill
    -0.05
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.05
     below
    -0.05
    985
    -0.05
    POSITIVE LOGITS
    orage
    0.08
    odos
    0.07
    ACE
    0.07
    ÑĤаж
    0.07
    ventus
    0.07
    avax
    0.07
    ÏĨÎŃ
    0.07
    ertools
    0.07
    çijŁ
    0.06
    ovny
    0.06
    Activations Density 0.007%

    No Known Activations