© 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. 128971
    Prev
    Next
    INDEX
    Explanations

    numerical values and citations in academic contexts

    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
    rypton
    -0.07
    oga
    -0.07
    idl
    -0.06
    berger
    -0.06
    liga
    -0.06
    DEM
    -0.06
    cmc
    -0.06
    league
    -0.06
    INES
    -0.06
    _PCM
    -0.06
    POSITIVE LOGITS
    anza
    0.07
    ãĥĥãĥĪ
    0.06
    nero
    0.06
    خرج
    0.06
    etail
    0.06
    ddit
    0.06
    ghan
    0.06
    ropp
    0.06
    ioni
    0.06
    à¤Ī
    0.06
    Activations Density 0.025%

    No Known Activations