© 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. 40724
    Prev
    Next
    INDEX
    Explanations

    terms related to restrictions and limitations concerning technology usage

    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
     EITHER
    -0.09
    GenerationStrategy
    -0.08
    /Instruction
    -0.07
    ãģ¾ãģļ
    -0.07
    OffsetTable
    -0.07
    senal
    -0.07
    apgolly
    -0.07
     quelque
    -0.07
    either
    -0.06
    Ahead
    -0.06
    POSITIVE LOGITS
     ones
    0.13
     others
    0.12
     thereof
    0.12
     other
    0.12
     them
    0.11
     similarly
    0.10
     it
    0.10
     also
    0.09
    'autres
    0.09
    åħ¶ä»ĸ
    0.09
    Activations Density 0.186%

    No Known Activations