© 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. 60613
    Prev
    Next
    INDEX
    Explanations

    references to additional related content or sources

    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
    acs
    -0.07
    etas
    -0.07
    ÑĢоÑģÑĤо
    -0.06
    istes
    -0.06
    arius
    -0.06
    rvé
    -0.06
    anning
    -0.06
    ogan
    -0.06
     Sher
    -0.06
    agos
    -0.06
    POSITIVE LOGITS
    å¬
    0.07
    çĶ
    0.07
     Xiao
    0.07
    _altern
    0.06
    оÑĤи
    0.06
    èŀ
    0.06
    ç
    0.06
     babe
    0.06
    å°Ĭ
    0.06
     Matches
    0.06
    Activations Density 0.001%

    No Known Activations