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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 26047
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" and its conjugations

    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
    ilia
    -0.15
    ulace
    -0.15
    éĥİ
    -0.15
    apons
    -0.15
     вÑģÑĤ
    -0.15
     sticker
    -0.14
    ulfilled
    -0.14
    ãng
    -0.14
    536
    -0.14
     Robin
    -0.14
    POSITIVE LOGITS
    nad
    0.16
    ((-
    0.15
    apl
    0.15
    tica
    0.15
    æ¾
    0.14
    athe
    0.14
    alen
    0.14
    andard
    0.14
    ehr
    0.13
    InSeconds
    0.13
    Activations Density 0.011%

    No Known Activations