© 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. 5-LLAMASCOPE-RES-131K
    11. 126051
    Prev
    Next
    INDEX
    Explanations

    references to television episodes and their descriptions

    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
    ÑĥзÑĭ
    -0.07
     Pey
    -0.07
     vys
    -0.07
    kan
    -0.06
    OS
    -0.06
     Bak
    -0.06
    fully
    -0.06
    @student
    -0.06
    flip
    -0.06
    /inet
    -0.06
    POSITIVE LOGITS
    оÑĤов
    0.07
    atri
    0.07
    /GPL
    0.06
    ikes
    0.06
    -cn
    0.06
    aylight
    0.06
    arden
    0.06
    'gc
    0.06
    âĸ²
    0.06
    âķIJâķIJ
    0.06
    Activations Density 0.007%

    No Known Activations