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. 96145
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of being outside or away from a location or situation

    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
    nemonic
    -0.06
    amment
    -0.06
     Sphere
    -0.06
    cad
    -0.06
    elli
    -0.06
    clus
    -0.06
    cling
    -0.06
    eru
    -0.06
    zyst
    -0.06
    usement
    -0.06
    POSITIVE LOGITS
    iesen
    0.07
    IRMWARE
    0.07
    MBER
    0.07
    tere
    0.07
    Skeleton
    0.07
    ìŀ
    0.07
    Ñħодим
    0.06
    ÙĩÙĨ
    0.06
    LIKELY
    0.06
     ÙĪØ£ÙĨ
    0.06
    Activations Density 0.032%

    No Known Activations