© 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. 93529
    Prev
    Next
    INDEX
    Explanations

    the preposition "of."

    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
    OnInit
    -0.08
    ighbor
    -0.08
    Ä±ÅŁÄ±k
    -0.08
    xiety
    -0.07
    å¡ŀ
    -0.07
     PureComponent
    -0.07
    redicate
    -0.07
    _AMD
    -0.07
    umbledore
    -0.07
    ÑĬ
    -0.07
    POSITIVE LOGITS
     shall
    0.06
     my
    0.06
    omin
    0.05
     unstable
    0.05
     currently
    0.05
     diss
    0.05
    ìĹŃìĭľ
    0.05
    untas
    0.05
    m
    0.05
     Hist
    0.05
    Activations Density 0.000%

    No Known Activations