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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125196
    Prev
    Next
    INDEX
    Explanations

    references to templates or structured frameworks

    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
    warf
    -0.06
    aller
    -0.06
     Synthetic
    -0.06
     Adam
    -0.06
    _RM
    -0.06
    535
    -0.05
     UF
    -0.05
    ifest
    -0.05
    Ĥæķ°
    -0.05
    Adam
    -0.05
    POSITIVE LOGITS
    andle
    0.07
     bottoms
    0.07
    unction
    0.07
    utsch
    0.07
    otten
    0.07
     gag
    0.06
    andles
    0.06
    è£Ĥ
    0.06
    ret
    0.06
    ammad
    0.06
    Activations Density 0.000%

    No Known Activations