© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28710
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating existence or state, particularly with a focus on "to be."

    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
    urrect
    -0.06
     nar
    -0.06
     Jer
    -0.06
     Extras
    -0.06
    atk
    -0.06
     con
    -0.06
     continua
    -0.06
    ë°
    -0.06
    chal
    -0.05
     concent
    -0.05
    POSITIVE LOGITS
     stub
    0.08
    lage
    0.07
    thood
    0.07
    avian
    0.07
    à¸ŀ
    0.07
    icans
    0.06
    stub
    0.06
    íĥĦ
    0.06
    Äįen
    0.06
    yen
    0.06
    Activations Density 0.002%

    No Known Activations