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. 22-LLAMASCOPE-RES-32K
    6. 4916
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals, particularly in entertainment and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hab
    -0.17
    æ¯Ľ
    -0.15
    ACA
    -0.15
    sted
    -0.14
    ÑĤÑĥÑĢ
    -0.14
    isor
    -0.14
    Ø´ÙĪØ±
    -0.14
    rych
    -0.14
    allax
    -0.14
    ÏĦÏī
    -0.14
    POSITIVE LOGITS
     Smith
    0.24
     smith
    0.22
    Smith
    0.20
    -Smith
    0.19
    smith
    0.17
    .sm
    0.16
     Fresh
    0.16
    mith
    0.15
    (Collision
    0.15
     Dunn
    0.14
    Activations Density 0.016%

    No Known Activations