© 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 EvalsExportsAPI 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. 130484
    Prev
    Next
    INDEX
    Explanations

    terms related to social and organizational structures

    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
    atron
    -0.07
    ally
    -0.07
    asca
    -0.06
    anst
    -0.06
    adal
    -0.06
     McGu
    -0.06
    uÄį
    -0.06
    eger
    -0.06
    ellig
    -0.06
    anch
    -0.06
    POSITIVE LOGITS
     except
    0.11
    except
    0.09
     or
    0.09
     váºŃy
    0.09
     Except
    0.08
     but
    0.08
    piar
    0.07
     familiar
    0.07
    Except
    0.07
     similarly
    0.07
    Activations Density 0.035%

    No Known Activations