© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75689
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and references to groups

    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
    wang
    -0.06
    ebe
    -0.06
     èĪ
    -0.06
     neighb
    -0.06
    791
    -0.06
    emes
    -0.05
     irr
    -0.05
    tempt
    -0.05
    794
    -0.05
    irmed
    -0.05
    POSITIVE LOGITS
    Except
    0.09
    except
    0.08
     Except
    0.08
     except
    0.08
    ane
    0.07
    olk
    0.07
     μαζί
    0.07
    _ROLE
    0.07
    oin
    0.07
    share
    0.07
    Activations Density 0.042%

    No Known Activations