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. 25-LLAMASCOPE-RES-32K
    6. 10844
    Prev
    Next
    INDEX
    Explanations

    references to economic stability and market warnings

    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
     Victor
    -0.15
    riminator
    -0.15
     Xen
    -0.14
    globals
    -0.14
    orio
    -0.14
    anik
    -0.14
    enk
    -0.14
     Taiwanese
    -0.14
     dias
    -0.14
     xen
    -0.14
    POSITIVE LOGITS
     Enterprises
    0.17
     Reform
    0.17
     Circular
    0.16
    ?key
    0.16
     Demon
    0.15
     Pilot
    0.15
    åŁİ
    0.15
    Trial
    0.15
    одÑĥ
    0.15
    chas
    0.15
    Activations Density 0.039%

    No Known Activations