© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 982
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in code or structured text

    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
    roupe
    -0.07
    SKU
    -0.06
    amples
    -0.06
    lob
    -0.06
    igham
    -0.06
    oblin
    -0.06
    essler
    -0.06
    okane
    -0.06
    й
    -0.06
    elts
    -0.06
    POSITIVE LOGITS
    OKIE
    0.10
    .scalablytyped
    0.08
    Uvs
    0.08
    оÑĢаÑı
    0.07
    rq
    0.07
    hoot
    0.07
     ActionTypes
    0.07
    QUIRE
    0.07
    ména
    0.07
    ILLS
    0.07
    Activations Density 0.001%

    No Known Activations