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. 20-LLAMASCOPE-RES-32K
    6. 28369
    Prev
    Next
    INDEX
    Explanations

    negative expressions and statements of denial or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ually
    -0.15
     Rage
    -0.14
    pons
    -0.14
    utta
    -0.14
    hari
    -0.14
    adem
    -0.14
    Rated
    -0.14
    isini
    -0.14
    ú
    -0.13
    abox
    -0.13
    POSITIVE LOGITS
     any
    0.20
    ä»»ä½ķ
    0.20
    Any
    0.16
    _any
    0.16
    oÅĽci
    0.15
     rocket
    0.15
     anymore
    0.15
     اÙĦØŃÙĬاة
    0.15
    emand
    0.15
     Any
    0.15
    Activations Density 0.313%

    No Known Activations