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. 24-LLAMASCOPE-RES-32K
    6. 15215
    Prev
    Next
    INDEX
    Explanations

    phrases related to queries or requests to locate information or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    found
    -0.16
    FOUND
    -0.15
    urb
    -0.15
    iences
    -0.15
    eper
    -0.14
    ิà¸į
    -0.14
    kits
    -0.14
    alf
    -0.14
    ény
    -0.14
    .arm
    -0.14
    POSITIVE LOGITS
    lay
    0.28
    ings
    0.23
    DOMNode
    0.19
    ley
    0.19
    NavController
    0.19
    INGS
    0.18
    lays
    0.18
    LAY
    0.17
    LEY
    0.17
    myp
    0.17
    Activations Density 0.020%

    No Known Activations