© 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. 129409
    Prev
    Next
    INDEX
    Explanations

    references to ranking, strength, and response measures related to voting policies

    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
    inkle
    -0.07
    .tc
    -0.07
    ctl
    -0.06
    nob
    -0.06
    adients
    -0.06
    飯
    -0.06
     cr
    -0.06
    Embedded
    -0.06
    ãģķãĤī
    -0.06
     fra
    -0.05
    POSITIVE LOGITS
    uzz
    0.08
     unchanged
    0.07
     ìĭłê·ľ
    0.06
    eno
    0.06
    çĭĤ
    0.06
     âĸ²
    0.06
    emo
    0.06
     its
    0.06
    utan
    0.06
    ataka
    0.06
    Activations Density 0.004%

    No Known Activations