© 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. 94144
    Prev
    Next
    INDEX
    Explanations

    references to uniforms and their characteristics

    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
    chod
    -0.08
    SHA
    -0.07
    bos
    -0.07
    ember
    -0.07
    bags
    -0.07
    nt
    -0.07
     Cush
    -0.07
    AEA
    -0.07
    aca
    -0.06
    ụn
    -0.06
    POSITIVE LOGITS
    itarian
    0.10
    ity
    0.10
    ities
    0.10
    (Un
    0.08
    è¡¡
    0.08
    ication
    0.08
    ize
    0.07
    ed
    0.07
    idad
    0.07
    esco
    0.07
    Activations Density 0.008%

    No Known Activations