© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 17802
    Prev
    Next
    INDEX
    Explanations

    temporal phrases and transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§ĭ
    -0.16
    lexport
    -0.15
    viewer
    -0.15
    oq
    -0.14
    ningar
    -0.14
    antity
    -0.14
    abeth
    -0.13
    vell
    -0.13
    killer
    -0.13
    vn
    -0.13
    POSITIVE LOGITS
     few
    0.24
     knowing
    0.20
     wards
    0.19
     successful
    0.18
     careful
    0.17
     Few
    0.17
    few
    0.17
    -sales
    0.16
     khi
    0.16
     finish
    0.15
    Activations Density 0.079%

    No Known Activations