Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3514
    Prev
    Next
    INDEX
    Explanations

    terms related to journalism and media reporting

    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
    pth
    -0.06
    raki
    -0.06
    á»ĭch
    -0.06
     cane
    -0.06
    éľ
    -0.06
    _variation
    -0.06
     torpedo
    -0.06
    uner
    -0.06
    blade
    -0.06
     Walton
    -0.06
    POSITIVE LOGITS
     reporting
    0.07
     journalism
    0.07
    afil
    0.07
     freel
    0.07
    /report
    0.07
     journalists
    0.07
     embed
    0.07
     colleague
    0.07
    embed
    0.06
     freelance
    0.06
    Activations Density 0.021%

    No Known Activations