© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128200
    Prev
    Next
    INDEX
    Explanations

    intense descriptors associated with chaotic or energetic events

    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
    ValuePair
    -0.08
    /Instruction
    -0.08
    amon
    -0.08
    каÑģ
    -0.07
    chai
    -0.07
    hlas
    -0.07
    jedn
    -0.07
     addCriterion
    -0.07
    agues
    -0.07
    @student
    -0.07
    POSITIVE LOGITS
    -style
    0.07
     of
    0.07
    èĪ¬
    0.07
    -like
    0.07
    bef
    0.06
     proportions
    0.06
    ort
    0.06
     mode
    0.06
    istic
    0.06
    Patch
    0.06
    Activations Density 0.032%

    No Known Activations