© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" or variations of it, indicating a focus on totality or completeness in context

    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
    nad
    -0.19
    arem
    -0.17
    λÏī
    -0.15
    oba
    -0.15
    ispers
    -0.14
     Exceptions
    -0.14
    ache
    -0.14
    ayet
    -0.14
    мени
    -0.14
     Merkel
    -0.14
    POSITIVE LOGITS
     sorts
    0.56
     kinds
    0.55
     manner
    0.53
     types
    0.38
     sort
    0.37
    sort
    0.35
     kind
    0.34
     KIND
    0.33
     SORT
    0.33
     manners
    0.32
    Activations Density 0.065%

    No Known Activations