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. 22-LLAMASCOPE-RES-131K
    6. 5246
    Prev
    Next
    INDEX
    Explanations

    geographical references and navigation-related terms

    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
    érica
    -0.07
    okud
    -0.06
     Slut
    -0.06
     synd
    -0.06
    gaard
    -0.06
    Bes
    -0.06
    _except
    -0.06
    addtogroup
    -0.06
    uish
    -0.06
    ammen
    -0.06
    POSITIVE LOGITS
     as
    0.11
    even
    0.10
     ranging
    0.10
     even
    0.10
     аж
    0.09
     nawet
    0.09
     až
    0.09
    竣
    0.09
     dokonce
    0.08
     táºŃn
    0.08
    Activations Density 0.058%

    No Known Activations