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. 20-LLAMASCOPE-RES-32K
    6. 20635
    Prev
    Next
    INDEX
    Explanations

    references to the state of Texas

    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
    ials
    -0.15
    orf
    -0.15
    une
    -0.15
    joy
    -0.14
     skin
    -0.14
    gewater
    -0.14
    hl
    -0.14
    yet
    -0.14
    row
    -0.14
    ance
    -0.14
    POSITIVE LOGITS
     Instruments
    0.20
    chner
    0.16
    lob
    0.16
     Amar
    0.15
    erif
    0.15
     Abbott
    0.15
    moil
    0.15
    igu
    0.15
    oise
    0.15
    å¾Ħ
    0.15
    Activations Density 0.011%

    No Known Activations