© 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. 27038
    Prev
    Next
    INDEX
    Explanations

    mentions of regulations or requirements related to data breaches and compliance

    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
    avad
    -0.07
    angs
    -0.06
     LICENSE
    -0.06
     License
    -0.06
    witch
    -0.06
    485
    -0.06
    602
    -0.06
    hen
    -0.06
    _convert
    -0.06
     bestselling
    -0.06
    POSITIVE LOGITS
    жÑĥ
    0.08
     acronym
    0.07
    ideo
    0.07
    åºĦ
    0.07
    OMB
    0.07
    лага
    0.07
    caffe
    0.07
     ÑĥÑģл
    0.07
    _operand
    0.06
    .targets
    0.06
    Activations Density 0.007%

    No Known Activations