© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118526
    Prev
    Next
    INDEX
    Explanations

    Hungarian words or phrases

    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
    ãĥ³ãĥIJãĥ¼
    -0.06
    melon
    -0.06
    imli
    -0.06
     dot
    -0.06
    éĢŁ
    -0.06
    _ValueChanged
    -0.06
    blr
    -0.06
    ooks
    -0.06
    swire
    -0.06
     capt
    -0.05
    POSITIVE LOGITS
     Micha
    0.07
     باغ
    0.07
    ahren
    0.07
    اگ
    0.06
    ï¼ļ↵↵
    0.06
    divid
    0.06
    'gc
    0.06
    PURE
    0.06
    abel
    0.06
    links
    0.06
    Activations Density 0.005%

    No Known Activations