© 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. 17-LLAMASCOPE-RES-131K
    6. 84663
    Prev
    Next
    INDEX
    Explanations

    programming language syntax that specifies memory management

    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
    ennie
    -0.06
    imson
    -0.06
    our
    -0.06
    vil
    -0.06
    ıf
    -0.06
     zeal
    -0.06
    its
    -0.05
    anga
    -0.05
     Harper
    -0.05
    bs
    -0.05
    POSITIVE LOGITS
    SWG
    0.07
    ircular
    0.07
    izo
    0.07
    ancellable
    0.07
    legen
    0.07
     Sesso
    0.07
    .netbeans
    0.07
    askell
    0.06
     Polo
    0.06
     tük
    0.06
    Activations Density 0.001%

    No Known Activations