© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129775
    Prev
    Next
    INDEX
    Explanations

    references to locations and places within a biographical context

    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
    hec
    -0.07
    ľ
    -0.07
     Incoming
    -0.07
    åª
    -0.07
    Ïģαβ
    -0.07
    contro
    -0.06
    abil
    -0.06
     pitch
    -0.06
     incoming
    -0.06
    ymph
    -0.06
    POSITIVE LOGITS
    ìĿ´ìĬ¤
    0.07
    بط
    0.06
    xing
    0.06
    &q
    0.06
    .previous
    0.06
    ernal
    0.06
    tember
    0.06
    _death
    0.06
    ãĥ¬ãĥĵ
    0.06
    ìĥĿ
    0.06
    Activations Density 0.006%

    No Known Activations