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. 3-LLAMASCOPE-RES-32K
    6. 213
    Prev
    Next
    INDEX
    Explanations

    expressions of high admiration or extraordinary quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adora
    -0.17
     provision
    -0.16
    sch
    -0.15
     miserable
    -0.15
    bie
    -0.14
    innen
    -0.14
    ÑĢоÑĪ
    -0.14
    adores
    -0.14
    ylv
    -0.14
    byname
    -0.13
    POSITIVE LOGITS
     feats
    0.18
     extents
    0.16
    IFT
    0.15
    .scala
    0.15
    amoto
    0.14
    irez
    0.14
    redient
    0.14
    Ù
    0.14
     extent
    0.14
     næ
    0.13
    Activations Density 0.015%

    No Known Activations