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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-LLAMASCOPE-RES-32K
    6. 18864
    Prev
    Next
    INDEX
    Explanations

    phrases related to after-school activities and programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shed
    -0.17
    swick
    -0.17
    contres
    -0.17
    soever
    -0.16
    hlen
    -0.16
    solete
    -0.15
    estring
    -0.15
    swagen
    -0.15
    erval
    -0.15
    usty
    -0.15
    POSITIVE LOGITS
    thought
    0.20
    amble
    0.18
    effects
    0.16
    mentioned
    0.16
    noon
    0.16
    884
    0.15
    733
    0.15
    278
    0.15
    ÅĻez
    0.15
    ocket
    0.15
    Activations Density 0.060%

    No Known Activations