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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84142
    Prev
    Next
    INDEX
    Explanations

    references to public organizations or entities

    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
    akis
    -0.06
    acas
    -0.06
    ÑĥÑĢн
    -0.06
    issen
    -0.06
    ettel
    -0.06
    ollo
    -0.06
    chner
    -0.06
    %A
    -0.06
     âĵĺ
    -0.06
     Rosenstein
    -0.06
    POSITIVE LOGITS
    uy
    0.07
    imson
    0.07
    kah
    0.06
    ongan
    0.06
    ileÅŁ
    0.06
    esser
    0.06
    bakan
    0.06
    олеÑĤ
    0.06
    igel
    0.06
    nty
    0.06
    Activations Density 0.000%

    No Known Activations