© 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. 3925
    Prev
    Next
    INDEX
    Explanations

    references to various forms of media and communication channels

    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
    eder
    -0.07
    oler
    -0.06
    cher
    -0.06
    ladıģı
    -0.06
    121
    -0.06
     Ñģобой
    -0.06
    ÑģÑı
    -0.06
    chers
    -0.06
    556
    -0.06
    elo
    -0.06
    POSITIVE LOGITS
    /on
    0.07
    upal
    0.07
    /by
    0.07
    /social
    0.06
    nip
    0.06
    -Javadoc
    0.06
    GMEM
    0.06
    iddet
    0.06
    ensa
    0.06
    izzo
    0.06
    Activations Density 0.027%

    No Known Activations