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. 27-LLAMASCOPE-RES-32K
    6. 10696
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of abundance or greater value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fty
    -0.15
    uffer
    -0.15
    upa
    -0.14
    ODEV
    -0.14
    allon
    -0.14
    ëģĶ
    -0.13
    krom
    -0.13
    ToLocal
    -0.13
    æī±
    -0.13
    ffi
    -0.13
    POSITIVE LOGITS
     more
    0.52
     much
    0.45
     than
    0.43
     hơn
    0.40
     beyond
    0.37
    more
    0.36
     MORE
    0.34
     More
    0.34
     far
    0.33
    More
    0.32
    Activations Density 0.091%

    No Known Activations