© 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. 17-LLAMASCOPE-RES-131K
    11. 76874
    Prev
    Next
    INDEX
    Explanations

    references to destruction and casualties in conflict situations

    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
    -fontawesome
    -0.09
    ijkstra
    -0.08
    ÑĢониÑĩеÑģ
    -0.08
    isposable
    -0.07
    _ASSUME
    -0.07
    _icall
    -0.07
    izards
    -0.07
    occo
    -0.07
     Î
    -0.07
    ---@
    -0.07
    POSITIVE LOGITS
    nal
    0.07
    %C
    0.07
     Courtesy
    0.07
    Ãķ
    0.06
    &nbsp
    0.06
    Courtesy
    0.06
    âĶ¬
    0.06
    <br
    0.06
    BYTE
    0.06
    \-
    0.06
    Activations Density 0.010%

    No Known Activations