© 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. 17-LLAMASCOPE-RES-131K
    11. 87360
    Prev
    Next
    INDEX
    Explanations

    elements related to publicity and media influence

    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
     Gros
    -0.07
    asca
    -0.07
     optimism
    -0.06
    eda
    -0.06
    imus
    -0.06
     blind
    -0.06
    imit
    -0.06
    aves
    -0.06
    ils
    -0.06
    uide
    -0.06
    POSITIVE LOGITS
     attention
    0.11
    attention
    0.10
     Attention
    0.10
    Attention
    0.09
     media
    0.09
    media
    0.08
    _attention
    0.08
    NewItem
    0.07
     Oxygen
    0.07
    amedi
    0.07
    Activations Density 0.022%

    No Known Activations