Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77149
    Prev
    Next
    INDEX
    Explanations

    legal terminology and definitions

    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
    ensa
    -0.08
    ossal
    -0.07
    pliers
    -0.06
     cellForRowAt
    -0.06
    ocre
    -0.06
    stry
    -0.06
    ardy
    -0.06
    iosper
    -0.06
    uber
    -0.06
     PIL
    -0.06
    POSITIVE LOGITS
     Plus
    0.07
     PLUS
    0.06
    inus
    0.06
    Plus
    0.06
    åķ¦
    0.06
     olup
    0.06
    á»Ŀi
    0.06
    ivid
    0.06
    ิร
    0.06
     bay
    0.06
    Activations Density 0.013%

    No Known Activations