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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96194
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" indicating location or context

    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
    odash
    -0.07
    intl
    -0.07
    еÑĢе
    -0.07
    åĪĹ
    -0.07
     IconData
    -0.07
    dden
    -0.07
    å»·
    -0.07
    ضÛĮ
    -0.07
    éré
    -0.07
     bindActionCreators
    -0.07
    POSITIVE LOGITS
    æ»ij
    0.06
    hq
    0.05
     Nap
    0.05
     Bret
    0.05
    achts
    0.05
    razier
    0.05
    (Parameter
    0.05
    allo
    0.05
    160
    0.05
     age
    0.05
    Activations Density 0.000%

    No Known Activations