© 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. 77377
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing actions or events

    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
    ify
    -0.06
    éij
    -0.06
    µľ
    -0.06
    ulg
    -0.06
    woke
    -0.06
    spin
    -0.06
    157
    -0.05
     aj
    -0.05
     Wake
    -0.05
     wake
    -0.05
    POSITIVE LOGITS
     happening
    0.09
    appen
    0.08
    zas
    0.08
    aec
    0.07
    leen
    0.07
     happened
    0.07
     happens
    0.07
    otten
    0.07
     happen
    0.07
    ober
    0.07
    Activations Density 0.006%

    No Known Activations