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. 23-LLAMASCOPE-RES-32K
    6. 15131
    Prev
    Next
    INDEX
    Explanations

    references to different types of stones, particularly those used in construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leine
    -0.15
     metallic
    -0.15
     cod
    -0.15
     McCorm
    -0.14
    intree
    -0.14
     pus
    -0.14
    ë§Ŀ
    -0.14
     Staples
    -0.14
    abin
    -0.13
     padded
    -0.13
    POSITIVE LOGITS
     stone
    0.54
     stones
    0.49
     Stone
    0.44
    Stone
    0.42
    stone
    0.41
    çŁ³
    0.41
     quar
    0.39
     quarry
    0.39
    stones
    0.39
     Stones
    0.38
    Activations Density 0.111%

    No Known Activations