© 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. 103692
    Prev
    Next
    INDEX
    Explanations

    references to news reports and studies concerning health and safety issues

    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
    lesc
    -0.06
     componentDid
    -0.06
    qu
    -0.06
    couz
    -0.06
    .ov
    -0.06
    _allocate
    -0.06
    anut
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    ollar
    -0.06
    ichtig
    -0.06
    POSITIVE LOGITS
     suggests
    0.07
    regor
    0.07
    ków
    0.06
     involving
    0.06
     suggest
    0.06
     Hari
    0.06
     indicates
    0.06
    697
    0.06
     showed
    0.06
    __["
    0.06
    Activations Density 0.030%

    No Known Activations