© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95670
    Prev
    Next
    INDEX
    Explanations

    phrases indicating audience engagement or involvement

    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
    ikal
    -0.07
    egl
    -0.07
    filer
    -0.07
    kes
    -0.06
    tb
    -0.06
    _nf
    -0.06
    fal
    -0.06
    yms
    -0.06
    pell
    -0.06
    aç
    -0.06
    POSITIVE LOGITS
    eland
    0.07
    irth
    0.06
    ople
    0.06
    bakan
    0.06
    lamaz
    0.06
     **)&
    0.06
    ONUS
    0.06
    اراÙĨ
    0.06
    linger
    0.06
    pton
    0.06
    Activations Density 0.002%

    No Known Activations