© 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. 103980
    Prev
    Next
    INDEX
    Explanations

    references to industry standards and organizations related to technology and security

    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
    elman
    -0.07
     defaultManager
    -0.07
    ervations
    -0.07
    á¿¶
    -0.06
    aeda
    -0.06
    è¸ı
    -0.06
     Seznam
    -0.06
    -Line
    -0.06
    uild
    -0.06
    iq
    -0.06
    POSITIVE LOGITS
    .org
    0.07
    indre
    0.07
    .gov
    0.07
    ãĥ¼ãĥģ
    0.07
     fitte
    0.06
     '../../../../../
    0.06
    arias
    0.06
    JsonValue
    0.06
    onec
    0.06
    ization
    0.06
    Activations Density 0.022%

    No Known Activations