© 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. 22-LLAMASCOPE-RES-131K
    11. 4080
    Prev
    Next
    INDEX
    Explanations

    references to physical positioning or placement

    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
    ullan
    -0.07
    ouis
    -0.07
    uchen
    -0.07
    orthand
    -0.07
    403
    -0.07
    ÙĪزÙĩ
    -0.07
    pora
    -0.07
    ÅĻad
    -0.07
    ربÙĬØ©
    -0.07
    quette
    -0.06
    POSITIVE LOGITS
     foot
    0.36
     Foot
    0.28
    foot
    0.28
     feet
    0.25
    -foot
    0.25
    Foot
    0.24
    _foot
    0.22
     FOOT
    0.21
     footprint
    0.20
     Feet
    0.20
    Activations Density 0.020%

    No Known Activations