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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61155
    Prev
    Next
    INDEX
    Explanations

    disparities and injustices related to race and social 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
    pls
    -0.08
    ieu
    -0.08
    ypse
    -0.07
    noinspection
    -0.07
     Minimum
    -0.07
    andest
    -0.07
    룡
    -0.07
    IEW
    -0.07
    볨
    -0.07
    vfs
    -0.06
    POSITIVE LOGITS
     proportion
    0.16
     disproportionate
    0.16
     disproportion
    0.15
     disproportionately
    0.14
     proportional
    0.12
     ratio
    0.12
     proport
    0.11
     relative
    0.11
    æ¯Ķä¾ĭ
    0.11
     dispro
    0.10
    Activations Density 0.037%

    No Known Activations