© 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. 15-LLAMASCOPE-RES-131K
    6. 103586
    Prev
    Next
    INDEX
    Explanations

    phrases related to different generations and their associated characteristics or roles

    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
    weed
    -0.08
    eteria
    -0.07
    akk
    -0.07
    ektor
    -0.06
    Ø©
    -0.06
     recent
    -0.06
    ordes
    -0.06
    ognito
    -0.06
    iec
    -0.06
    å½ĵåīį
    -0.06
    POSITIVE LOGITS
    876
    0.08
    /new
    0.07
     Wig
    0.06
    CKET
    0.06
    rench
    0.06
    -generation
    0.06
    -old
    0.06
    /class
    0.06
    ãģĦãĤĦ
    0.06
    ycop
    0.06
    Activations Density 0.005%

    No Known Activations