© 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. 15-LLAMASCOPE-RES-131K
    11. 103981
    Prev
    Next
    INDEX
    Explanations

    common prepositions and relational phrases in the text

    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
     a
    -0.07
    pedia
    -0.07
    poser
    -0.07
    ÑĢой
    -0.06
    aeda
    -0.06
    .qq
    -0.06
    alis
    -0.06
     something
    -0.05
     an
    -0.05
     some
    -0.05
    POSITIVE LOGITS
    both
    0.20
     both
    0.19
     BOTH
    0.17
    _both
    0.17
     beide
    0.17
    Both
    0.17
     ambos
    0.16
     обо
    0.16
     Both
    0.15
     obou
    0.14
    Activations Density 0.022%

    No Known Activations