Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 3236
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes related to professional roles and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latter
    -0.27
    egative
    -0.26
    olume
    -0.24
    orthy
    -0.21
    eneric
    -0.20
    coration
    -0.20
    quiv
    -0.20
    flammatory
    -0.19
    scious
    -0.19
    rokes
    -0.19
    POSITIVE LOGITS
    /-
    0.28
    ftware
    0.22
    ropriate
    0.21
    jectory
    0.21
    apons
    0.21
    ufact
    0.20
    incipal
    0.20
    acters
    0.19
    ernet
    0.18
    dated
    0.18
    Activations Density 0.232%

    No Known Activations