© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29039
    Prev
    Next
    INDEX
    Explanations

    references to legal claims and compensations for injuries or damages

    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
    isku
    -0.07
     suicidal
    -0.07
    URRE
    -0.07
    beam
    -0.07
    бо
    -0.07
    iffe
    -0.07
    éĢĥ
    -0.06
    ?option
    -0.06
    embro
    -0.06
    dra
    -0.06
    POSITIVE LOGITS
     damages
    0.12
     damage
    0.11
     Dam
    0.10
     lost
    0.10
     loss
    0.10
     losses
    0.10
     dam
    0.10
    dam
    0.10
     injury
    0.09
     Injury
    0.09
    Activations Density 0.014%

    No Known Activations