© 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. 71442
    Prev
    Next
    INDEX
    Explanations

    terms related to archival content or documentation

    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
    esk
    -0.07
    keit
    -0.07
    igo
    -0.06
    DAL
    -0.06
    atus
    -0.06
    erate
    -0.06
    ney
    -0.06
    uhn
    -0.06
    rey
    -0.06
    longleftrightarrow
    -0.06
    POSITIVE LOGITS
    ssp
    0.07
    ãĥ¼ãĥijãĥ¼
    0.07
    orca
    0.07
    URI
    0.07
    ksiyon
    0.06
    æĽ¾
    0.06
     اÙĦرØŃ
    0.06
    irtual
    0.06
    atron
    0.06
    .sb
    0.06
    Activations Density 0.002%

    No Known Activations