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. 24-LLAMASCOPE-RES-32K
    6. 5799
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm and obsession with content creators and their works

    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
     continual
    -0.17
     allowable
    -0.16
    uib
    -0.16
     roadway
    -0.15
    ÙĪØ§ÙĨ
    -0.14
    วร
    -0.14
     sez
    -0.14
    (MPI
    -0.14
    ยà¸ĩ
    -0.14
     seperate
    -0.13
    POSITIVE LOGITS
     âĢŀ
    0.18
     splitted
    0.18
     nr
    0.17
     cca
    0.17
     disproportion
    0.17
    âĢŀ
    0.17
    irut
    0.16
    wich
    0.15
     воÑĤ
    0.15
    о
    0.15
    Activations Density 1.513%

    No Known Activations