© 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. 93485
    Prev
    Next
    INDEX
    Explanations

    occurrences of names, particularly "Roland" and "Ronald."

    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
    oit
    -0.08
    алеж
    -0.07
    itably
    -0.07
    872
    -0.07
    reon
    -0.06
    ToBounds
    -0.06
    961
    -0.06
    232
    -0.06
    annon
    -0.06
    енз
    -0.06
    POSITIVE LOGITS
    ayne
    0.09
    ussen
    0.07
    ius
    0.06
    aden
    0.06
    ormal
    0.06
    ipples
    0.06
    mil
    0.06
    rib
    0.06
     damping
    0.06
    ãĥ«ãĥī
    0.06
    Activations Density 0.005%

    No Known Activations