© 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. 40287
    Prev
    Next
    INDEX
    Explanations

    references to age and experience

    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
    quier
    -0.07
    Shock
    -0.06
    ombat
    -0.06
    holm
    -0.06
    ola
    -0.06
    ofi
    -0.06
    æĭŁ
    -0.06
     Stereo
    -0.06
    akis
    -0.06
    eper
    -0.06
    POSITIVE LOGITS
     unfamiliar
    0.12
     familiarity
    0.10
     background
    0.10
     familiar
    0.09
     Recall
    0.09
     Background
    0.08
    -background
    0.08
     BACKGROUND
    0.08
    _background
    0.08
    Background
    0.08
    Activations Density 0.054%

    No Known Activations