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. 15230
    Prev
    Next
    INDEX
    Explanations

    specific information related to legal proceedings and documentation

    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
    íĺģ
    -0.15
     adel
    -0.15
    .LOG
    -0.15
     Fen
    -0.14
    ively
    -0.14
    legt
    -0.14
    anke
    -0.14
    彦
    -0.14
     Lans
    -0.14
     Hop
    -0.14
    POSITIVE LOGITS
    alice
    0.17
    bris
    0.16
    antas
    0.16
     Aeros
    0.16
     Label
    0.15
     NH
    0.15
    NF
    0.15
     Silk
    0.15
    atar
    0.14
    Wins
    0.14
    Activations Density 0.066%

    No Known Activations