© 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. 4296
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

    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
    rooms
    -0.09
    shed
    -0.07
    rowning
    -0.07
     sheds
    -0.07
     rooms
    -0.07
     обол
    -0.07
    âu
    -0.07
    анÑĤи
    -0.06
    umbs
    -0.06
    wn
    -0.06
    POSITIVE LOGITS
     cm
    0.10
     sink
    0.09
    cm
    0.09
     foot
    0.09
     inches
    0.09
     Inches
    0.08
     CM
    0.08
    _cm
    0.08
     bowl
    0.08
     inch
    0.08
    Activations Density 0.058%

    No Known Activations