© 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. 70645
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and keywords

    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
    ongs
    -0.06
    ŀ
    -0.06
    aur
    -0.06
    opr
    -0.05
    kart
    -0.05
     steer
    -0.05
    theid
    -0.05
    ahoma
    -0.05
     parted
    -0.05
    .isdigit
    -0.05
    POSITIVE LOGITS
     Pla
    0.08
    ÏĦικα
    0.07
    _AST
    0.07
     SPDX
    0.07
     @$
    0.07
    RuleContext
    0.07
    peg
    0.07
     BÃŃ
    0.07
    ABCDEFGHIJKLMNOP
    0.06
    ParameterValue
    0.06
    Activations Density 0.010%

    No Known Activations