© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4326
    Prev
    Next
    INDEX
    Explanations

    references to familiarity and shared experiences

    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
    cid
    -0.06
    nock
    -0.06
    eci
    -0.06
    -prepend
    -0.06
    ebek
    -0.06
    pio
    -0.06
    readcr
    -0.06
    PG
    -0.06
    eger
    -0.06
    pha
    -0.06
    POSITIVE LOGITS
     familiar
    0.39
    amiliar
    0.29
     familiarity
    0.28
     Fam
    0.27
    çĨŁ
    0.21
     acquainted
    0.18
     unfamiliar
    0.17
     fam
    0.17
     recognizable
    0.13
     famil
    0.12
    Activations Density 0.130%

    No Known Activations