© 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. 16141
    Prev
    Next
    INDEX
    Explanations

    terms related to "clip" in various contexts

    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
    ลาย
    -0.07
    umer
    -0.07
    UPPORTED
    -0.06
     planets
    -0.06
    ÄĽk
    -0.06
    -gnu
    -0.06
    estar
    -0.06
    á»±c
    -0.06
    strt
    -0.06
    ummies
    -0.06
    POSITIVE LOGITS
    per
    0.10
    pered
    0.08
    otal
    0.08
    pling
    0.08
    olar
    0.08
    adelphia
    0.08
    pery
    0.07
    adel
    0.07
    PER
    0.07
    åĪ»
    0.07
    Activations Density 0.006%

    No Known Activations