© 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. 78716
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "pointing out" and variations of the word "out"

    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
    o
    -0.06
     Glover
    -0.06
    uyu
    -0.06
    èijī
    -0.06
    åı¶
    -0.06
    /part
    -0.06
    ê´Ģ
    -0.06
     buá»Ļc
    -0.06
    according
    -0.06
    raud
    -0.06
    POSITIVE LOGITS
     how
    0.08
     bahwa
    0.07
     rằng
    0.07
    iddy
    0.07
     ìĤ¬íķŃ
    0.07
     that
    0.07
    ÑĤеÑĢн
    0.07
    tains
    0.06
    itura
    0.06
    earn
    0.06
    Activations Density 0.007%

    No Known Activations