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. 16707
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific theories and explanations

    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
    alah
    -0.16
    åħ¸
    -0.15
     Techniques
    -0.13
     Guar
    -0.13
    .WinForms
    -0.13
     prakt
    -0.13
     colorWithRed
    -0.13
    engin
    -0.13
    .readValue
    -0.13
    大åħ¨
    -0.13
    POSITIVE LOGITS
     explanation
    0.50
     explanations
    0.49
     hypothesis
    0.41
     Explanation
    0.40
     theories
    0.38
    Explanation
    0.37
     explaining
    0.36
     theory
    0.36
     explain
    0.36
     hypotheses
    0.35
    Activations Density 0.271%

    No Known Activations