© 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. 83159
    Prev
    Next
    INDEX
    Explanations

    distinct identifiers or notable terms in various 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
     nto
    -0.07
     QuáºŃn
    -0.07
     coi
    -0.07
    ï½£
    -0.07
     sáng
    -0.07
    ï¼ľ
    -0.06
    обÑĢаз
    -0.06
    opsis
    -0.06
    naz
    -0.06
    ष
    -0.06
    POSITIVE LOGITS
    uye
    0.07
    onest
    0.06
    imbus
    0.06
    chin
    0.06
    ycop
    0.06
    iyel
    0.06
    urons
    0.06
    uese
    0.06
    pras
    0.06
    acente
    0.06
    Activations Density 0.003%

    No Known Activations