© 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. 28825
    Prev
    Next
    INDEX
    Explanations

    references to water flow and its direction in relation to specific locations

    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
    ãĥ¼ãĥį
    -0.08
    çīĩ
    -0.07
    eln
    -0.07
    ForResult
    -0.07
    estro
    -0.07
    .kode
    -0.07
     zemi
    -0.07
    è²¼
    -0.06
    olumn
    -0.06
     ngang
    -0.06
    POSITIVE LOGITS
    /down
    0.15
    ing
    0.10
    -down
    0.10
    /up
    0.10
    /out
    0.09
    /off
    0.09
    ed
    0.08
    ers
    0.08
    /back
    0.08
    itzer
    0.07
    Activations Density 0.008%

    No Known Activations