© 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. 78400
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality of films or performances

    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
    igh
    -0.07
    ordan
    -0.07
    isser
    -0.06
     latest
    -0.06
    andles
    -0.06
     thing
    -0.06
    .xtext
    -0.06
     ê²ĥ
    -0.06
    idi
    -0.06
    id
    -0.06
    POSITIVE LOGITS
    llib
    0.07
    ÙĦÙĪب
    0.07
     CascadeType
    0.07
    dac
    0.07
    ADER
    0.06
     cast
    0.06
     soundtrack
    0.06
    ãĥĪãĥª
    0.06
    οÏįÏĤ
    0.06
    Proto
    0.06
    Activations Density 0.025%

    No Known Activations