© 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. 118304
    Prev
    Next
    INDEX
    Explanations

    references to risks and risk factors

    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
    iska
    -0.07
    éĢł
    -0.07
    pany
    -0.07
    irl
    -0.06
    uration
    -0.06
    stva
    -0.06
    gere
    -0.06
     ==============================================================
    -0.06
    awan
    -0.06
    upil
    -0.06
    POSITIVE LOGITS
    lessly
    0.09
    ier
    0.09
     factors
    0.07
    iest
    0.07
    iness
    0.07
    tober
    0.07
     Factors
    0.07
    омеÑĢ
    0.07
    averse
    0.07
    door
    0.07
    Activations Density 0.012%

    No Known Activations