© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    elements related to video game mechanics and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Fragments of text from video game reviews, descriptions, and discussions, often highlighting game titles, quality assessments, or feature descriptions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    osaur
    -0.07
    onnen
    -0.06
    orida
    -0.06
    stab
    -0.06
     Equality
    -0.06
    stral
    -0.06
    battle
    -0.06
    amel
    -0.06
    ammer
    -0.06
    lacak
    -0.06
    POSITIVE LOGITS
    ogne
    0.08
    ignum
    0.07
    Callable
    0.07
    Agent
    0.07
     missions
    0.06
    }elseif
    0.06
    ovenant
    0.06
    cia
    0.06
     circum
    0.06
    PTH
    0.06
    Activations Density 0.016%

    No Known Activations