© 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. 125900
    Prev
    Next
    INDEX
    Explanations

    references to software versions

    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
    jang
    -0.07
    EMPL
    -0.06
    app
    -0.06
    iang
    -0.06
    ovation
    -0.06
     Bai
    -0.05
    addy
    -0.05
    ent
    -0.05
    ÃŃ
    -0.05
     Gra
    -0.05
    POSITIVE LOGITS
    .Version
    0.09
    istas
    0.09
    HeaderCode
    0.08
    .VERSION
    0.08
    ality
    0.07
    OffsetTable
    0.07
    erosis
    0.07
    ahat
    0.07
    ocab
    0.07
    upgrade
    0.07
    Activations Density 0.014%

    No Known Activations