© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90291
    Prev
    Next
    INDEX
    Explanations

    contractions of the verb "to be" used for possession

    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
    tero
    -0.08
    .AspNet
    -0.07
    ле
    -0.07
     bergen
    -0.07
    ught
    -0.07
    edback
    -0.07
    thon
    -0.07
    ovich
    -0.07
    kses
    -0.06
    uguay
    -0.06
    POSITIVE LOGITS
    _go
    0.07
     go
    0.07
    -go
    0.06
    ढ
    0.06
    eder
    0.06
    251
    0.06
    imm
    0.06
    仪
    0.06
    aba
    0.06
    Go
    0.06
    Activations Density 0.008%

    No Known Activations