© 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. 30-LLAMASCOPE-RES-32K
    11. 23296
    Prev
    Next
    INDEX
    Explanations

    references to theatre and performance-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theatre
    -0.23
     Theater
    -0.22
     theater
    -0.21
     theaters
    -0.20
     theat
    -0.20
     theatre
    -0.20
    emale
    -0.19
    erator
    -0.18
     theatrical
    -0.17
    eness
    -0.16
    POSITIVE LOGITS
    -going
    0.26
    going
    0.23
     arts
    0.21
    go
    0.20
     Royal
    0.20
    ical
    0.19
    503
    0.18
    /music
    0.18
    -go
    0.18
    land
    0.18
    Activations Density 0.016%

    No Known Activations