© 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. 25-LLAMASCOPE-RES-32K
    6. 19186
    Prev
    Next
    INDEX
    Explanations

    terms related to educational courses and training programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endale
    -0.17
    egie
    -0.15
    VisualStyle
    -0.15
    ildo
    -0.15
    ustos
    -0.14
    ORIZ
    -0.14
    eid
    -0.14
    loth
    -0.14
     пÑĢа
    -0.14
    .GridColumn
    -0.14
    POSITIVE LOGITS
     course
    0.39
     participant
    0.38
     participants
    0.37
     instructor
    0.35
     class
    0.34
     Instructor
    0.34
     Participants
    0.33
     Participant
    0.31
     instructors
    0.31
     trainer
    0.30
    Activations Density 0.422%

    No Known Activations