© 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. 129236
    Prev
    Next
    INDEX
    Explanations

    references to contrasting or comparative perspectives

    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
    lü
    -0.07
    ecz
    -0.07
    amba
    -0.07
     themselves
    -0.07
     *(*
    -0.07
    ÑĨенÑĤÑĢа
    -0.07
    yla
    -0.07
    ucci
    -0.07
    linkplain
    -0.07
    าà¸Ķ
    -0.06
    POSITIVE LOGITS
     side
    0.09
     half
    0.08
    est
    0.08
    half
    0.07
    rea
    0.07
    world
    0.07
     extreme
    0.07
    hand
    0.07
     полов
    0.07
     Side
    0.07
    Activations Density 0.012%

    No Known Activations