© 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. 71109
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific non-English characters or symbols

    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
    hawk
    -0.07
     mold
    -0.06
    fos
    -0.06
    olds
    -0.06
    rei
    -0.06
    ileo
    -0.06
    má
    -0.06
    pherd
    -0.06
    fahren
    -0.06
    ivel
    -0.06
    POSITIVE LOGITS
    bservable
    0.08
    esta
    0.07
    اÙĬÙĨ
    0.07
    istic
    0.07
    erif
    0.07
    izzo
    0.07
    िसम
    0.07
    .ErrorCode
    0.06
    _VLAN
    0.06
    cha
    0.06
    Activations Density 0.003%

    No Known Activations