© 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. 22-LLAMASCOPE-RES-131K
    6. 4111
    Prev
    Next
    INDEX
    Explanations

    instances of negative outcomes or consequences

    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
    agan
    -0.07
    _DISABLE
    -0.07
    ilion
    -0.07
     nominal
    -0.07
    ứng
    -0.07
    ucci
    -0.07
    izr
    -0.07
    hop
    -0.06
    ventus
    -0.06
    itter
    -0.06
    POSITIVE LOGITS
     Comments
    0.07
    ufen
    0.07
     comments
    0.07
    825
    0.06
    aches
    0.06
    eln
    0.06
    ampo
    0.06
     Tun
    0.06
    ETCH
    0.06
     holidays
    0.06
    Activations Density 0.001%

    No Known Activations