© 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. 87174
    Prev
    Next
    INDEX
    Explanations

    references to authentication and authorization concepts

    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
    rana
    -0.08
    onis
    -0.07
    -eyed
    -0.07
    hood
    -0.07
    TURE
    -0.07
    igans
    -0.07
    tures
    -0.06
    IFF
    -0.06
    essen
    -0.06
    /octet
    -0.06
    POSITIVE LOGITS
    entic
    0.14
    enticator
    0.12
    enticated
    0.11
    ENTICATION
    0.10
    ORITY
    0.08
    etic
    0.08
    s
    0.08
    ENTIC
    0.08
    ORIZATION
    0.08
    entifier
    0.08
    Activations Density 0.005%

    No Known Activations