© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    references to theme park tickets and related offers

    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
    omin
    -0.06
     Cargo
    -0.06
    adata
    -0.06
    cargo
    -0.06
     cargo
    -0.06
    ÄĻp
    -0.06
     Hancock
    -0.06
    unami
    -0.06
    Humans
    -0.06
     dow
    -0.06
    POSITIVE LOGITS
    roke
    0.08
    -holder
    0.07
    elsen
    0.07
    atel
    0.07
    oucher
    0.07
     Rosenstein
    0.07
     holder
    0.07
    ssel
    0.07
     Holder
    0.07
    valueOf
    0.07
    Activations Density 0.002%

    No Known Activations