© 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. 17-LLAMASCOPE-RES-131K
    11. 71054
    Prev
    Next
    INDEX
    Explanations

    phrases that express memory or recollection

    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
    andre
    -0.07
    ei
    -0.06
     pii
    -0.06
    uesta
    -0.06
    PG
    -0.06
    AndView
    -0.06
    .GetObject
    -0.06
    aven
    -0.06
    abis
    -0.06
    iser
    -0.06
    POSITIVE LOGITS
     us
    0.11
     me
    0.08
    ÏĦαι
    0.08
    ingly
    0.07
    rik
    0.07
    -gnu
    0.07
    ively
    0.07
     itself
    0.07
    /rem
    0.07
     reminds
    0.07
    Activations Density 0.003%

    No Known Activations