© 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. 69578
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to characteristics or conditions

    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
    IFn
    -0.08
    ventus
    -0.08
    lak
    -0.08
    creens
    -0.08
    fet
    -0.08
     muschi
    -0.07
    ROUT
    -0.07
    hausen
    -0.07
     Erotische
    -0.07
    ênh
    -0.07
    POSITIVE LOGITS
     wings
    0.07
    1
    0.06
    446
    0.06
     Buckingham
    0.06
    0.06
    -headed
    0.06
     wing
    0.06
     DJ
    0.05
    ahren
    0.05
    Mech
    0.05
    Activations Density 0.000%

    No Known Activations