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. 22285
    Prev
    Next
    INDEX
    Explanations

    information related to processes and timelines

    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
    .pa
    -0.15
    ONA
    -0.15
    adele
    -0.15
    tero
    -0.14
     exceed
    -0.14
     Nearly
    -0.14
     Almost
    -0.14
    ceed
    -0.13
    wie
    -0.13
    abe
    -0.13
    POSITIVE LOGITS
     anywhere
    0.86
     somewhere
    0.61
     between
    0.60
    Anywhere
    0.52
    between
    0.51
     Between
    0.46
    Between
    0.44
     anything
    0.44
     zwischen
    0.43
     ranging
    0.42
    Activations Density 0.322%

    No Known Activations