© 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. 4430
    Prev
    Next
    INDEX
    Explanations

    concepts related to the relevance and impact of societal 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
    resse
    -0.08
    ebo
    -0.06
    nemonic
    -0.06
    inqu
    -0.06
    dech
    -0.06
     att
    -0.06
     Promise
    -0.06
    agt
    -0.06
    rone
    -0.06
    ivant
    -0.06
    POSITIVE LOGITS
    owl
    0.07
    igma
    0.07
    åıĬåħ¶
    0.07
     versus
    0.07
    éĥ¡
    0.06
     role
    0.06
    ìĽĥ
    0.06
     vs
    0.06
    ä¸ļ
    0.06
     fate
    0.06
    Activations Density 0.051%

    No Known Activations