© 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. 15-LLAMASCOPE-RES-131K
    11. 90265
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and terms indicating preference or likelihood

    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
    ifest
    -0.07
    AFX
    -0.07
    viron
    -0.06
    afc
    -0.06
    zen
    -0.06
     same
    -0.06
    rch
    -0.06
    Datas
    -0.06
    itals
    -0.06
    rophy
    -0.05
    POSITIVE LOGITS
     than
    0.13
    -than
    0.12
    Than
    0.11
     THAN
    0.11
     Than
    0.11
    than
    0.10
    _than
    0.10
     než
    0.08
     än
    0.08
    _THAN
    0.08
    Activations Density 0.029%

    No Known Activations