© 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. 119182
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a process or method

    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
    olas
    -0.07
    zza
    -0.06
    curring
    -0.06
    ica
    -0.06
    rip
    -0.06
    ilia
    -0.06
    aid
    -0.06
    ëĮĢë¡ľ
    -0.06
     Evel
    -0.06
     Hunts
    -0.06
    POSITIVE LOGITS
    ozÃŃ
    0.08
    put
    0.08
    ToProps
    0.07
     Giz
    0.07
    PUT
    0.07
    :\/\/
    0.07
    jeta
    0.07
    UNET
    0.07
     intermedi
    0.06
    alet
    0.06
    Activations Density 0.011%

    No Known Activations