© 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. 5-LLAMASCOPE-RES-131K
    11. 125598
    Prev
    Next
    INDEX
    Explanations

    references to efforts and initiatives aimed at addressing social or political issues

    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
    ovable
    -0.07
    ever
    -0.06
    assis
    -0.06
    _tl
    -0.06
    aille
    -0.06
     Bam
    -0.06
    mention
    -0.06
    ायन
    -0.06
     ga
    -0.06
    aison
    -0.06
    POSITIVE LOGITS
    OSP
    0.07
    иÑħ
    0.07
     Parties
    0.07
    Ñī
    0.06
     vé
    0.06
    ICES
    0.06
    ennes
    0.06
    екÑĤоÑĢ
    0.06
     hoa
    0.06
    ISTA
    0.06
    Activations Density 0.014%

    No Known Activations