© 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. 15-LLAMASCOPE-RES-131K
    11. 27056
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation and infrastructure

    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
    çī
    -0.08
    ertz
    -0.07
    Ùħت
    -0.06
    723
    -0.06
    utters
    -0.06
    .scalablytyped
    -0.06
    jin
    -0.06
    jom
    -0.06
    iously
    -0.06
    omb
    -0.06
    POSITIVE LOGITS
     whose
    0.10
     such
    0.08
    whose
    0.08
    _unicode
    0.07
    inese
    0.07
     like
    0.07
     Zimmerman
    0.06
     valido
    0.06
    oses
    0.06
    çIJ´
    0.06
    Activations Density 0.040%

    No Known Activations