© 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. 76961
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    orus
    -0.07
    eka
    -0.06
    ást
    -0.06
    åĸĦ
    -0.06
    erken
    -0.06
    oksen
    -0.06
    FAIL
    -0.06
    amel
    -0.06
    seau
    -0.06
     funcs
    -0.06
    POSITIVE LOGITS
    856
    0.06
     Gren
    0.06
    417
    0.06
     Silver
    0.06
    948
    0.06
    245
    0.05
     Steps
    0.05
    linger
    0.05
    808
    0.05
    ida
    0.05
    Activations Density 0.001%

    No Known Activations