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. 31-LLAMASCOPE-RES-32K
    6. 9784
    Prev
    Next
    INDEX
    Explanations

    references to significant life events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fifty
    -0.26
     forty
    -0.25
    ÛµÛ°
    -0.25
     seventy
    -0.24
     Forty
    -0.24
    Û´Û°
    -0.24
     Fifty
    -0.24
     sixty
    -0.23
     eighty
    -0.23
    Û³Û¶
    -0.23
    POSITIVE LOGITS
    29
    0.63
    28
    0.63
    27
    0.63
    26
    0.62
    31
    0.61
    25
    0.59
    24
    0.59
    30
    0.59
    23
    0.59
    22
    0.57
    Activations Density 0.344%

    No Known Activations