© 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. 9-LLAMASCOPE-RES-131K
    6. 95727
    Prev
    Next
    INDEX
    Explanations

    references to scheduling and timetables

    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
    age
    -0.08
    nage
    -0.08
    ager
    -0.07
    unes
    -0.07
    isan
    -0.06
    plevel
    -0.06
     scratch
    -0.06
    /she
    -0.06
    ordes
    -0.06
    obus
    -0.06
    POSITIVE LOGITS
    ../../../
    0.10
    uffix
    0.09
    autop
    0.09
    mak
    0.08
    WidgetItem
    0.08
    yntax
    0.07
    ãĥĥãĥī
    0.07
    æķ·
    0.07
    stration
    0.07
    gado
    0.07
    Activations Density 0.013%

    No Known Activations