© 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. 126383
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize personal opinions or subjective statements

    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
    nt
    -0.08
    ej
    -0.07
    eg
    -0.07
    hand
    -0.07
    ered
    -0.07
    iest
    -0.06
    evice
    -0.06
    och
    -0.06
    odore
    -0.06
    iams
    -0.06
    POSITIVE LOGITS
    Ìģ
    0.09
    lef
    0.09
    meli
    0.09
    Ì
    0.09
    anker
    0.09
    pha
    0.08
    ÌĨ
    0.08
    gii
    0.08
    maal
    0.08
    ÌĢ
    0.08
    Activations Density 0.014%

    No Known Activations