© 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. 103808
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their placements or descriptions in a scene or context

    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
    ja
    -0.07
    /trunk
    -0.07
    adb
    -0.07
     Underground
    -0.07
    983
    -0.07
    ahoo
    -0.06
    lav
    -0.06
    borg
    -0.06
    anj
    -0.06
    kehr
    -0.06
    POSITIVE LOGITS
     immediate
    0.07
     immediately
    0.07
     behind
    0.07
    iky
    0.07
    ITTE
    0.06
     close
    0.06
    ');?>"
    0.06
    ANCED
    0.06
     far
    0.06
     just
    0.06
    Activations Density 0.124%

    No Known Activations