© 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. 120916
    Prev
    Next
    INDEX
    Explanations

    terms related to official requirements or directives

    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
    dale
    -0.08
    ugg
    -0.07
    aqu
    -0.07
    iên
    -0.07
    adh
    -0.07
    spa
    -0.07
    ordin
    -0.07
    мм
    -0.07
    ight
    -0.07
    sko
    -0.07
    POSITIVE LOGITS
    çīĮ
    0.08
    ìĤ¬íķŃ
    0.08
    forth
    0.07
    reuse
    0.07
    estic
    0.07
    ev
    0.06
    eer
    0.06
    holder
    0.06
    åºĥ
    0.06
    ur
    0.06
    Activations Density 0.008%

    No Known Activations