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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-LLAMASCOPE-RES-32K
    6. 3595
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "being" and other related forms, as well as expressions of existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _mgr
    -0.14
    íĺij
    -0.14
    yclopedia
    -0.14
     tsl
    -0.14
     же
    -0.14
    úde
    -0.13
    ocene
    -0.13
    QR
    -0.13
     Sans
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
    ionario
    0.16
    ion
    0.15
     inve
    0.14
    owan
    0.14
    uye
    0.14
    ory
    0.14
     wre
    0.14
     continents
    0.14
    andler
    0.13
     Dump
    0.13
    Activations Density 0.176%

    No Known Activations