© 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. 22-LLAMASCOPE-RES-131K
    11. 4228
    Prev
    Next
    INDEX
    Explanations

    quotes and conditions related to user authentication

    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
     Aj
    -0.06
     Warsaw
    -0.06
     Dear
    -0.06
    inx
    -0.06
    reek
    -0.06
     Sp
    -0.06
     pres
    -0.06
     Ama
    -0.06
    Aws
    -0.06
    \Migrations
    -0.06
    POSITIVE LOGITS
     StringField
    0.11
     Flask
    0.11
     flask
    0.10
     SQLAlchemy
    0.09
     sqlalchemy
    0.08
    tf
    0.08
     WTF
    0.08
    _FLASH
    0.08
    .utcnow
    0.07
    PasswordField
    0.07
    Activations Density 0.000%

    No Known Activations