© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with various entertainment figures and their works

    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
    :UIAlert
    -0.07
    noinspection
    -0.07
    antar
    -0.07
    ather
    -0.07
    uby
    -0.06
    arth
    -0.06
    using
    -0.06
    å¦
    -0.06
    ijkstra
    -0.06
     MessageBoxButtons
    -0.06
    POSITIVE LOGITS
    ¶
    0.10
     |
    0.08
    ï½ľ
    0.08
     synonyms
    0.08
    .Extension
    0.07
     Kund
    0.07
     ayrıca
    0.07
     also
    0.07
     Cunningham
    0.07
    ndl
    0.06
    Activations Density 0.069%

    No Known Activations