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. 1867
    Prev
    Next
    INDEX
    Explanations

    patterns and connections related to retail and commerce

    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
    559
    -0.15
     G
    -0.15
    arna
    -0.15
     Vern
    -0.15
    ascus
    -0.14
    503
    -0.14
    ر
    -0.14
    aris
    -0.14
    .ga
    -0.13
    -r
    -0.13
    POSITIVE LOGITS
    -T
    0.18
    -t
    0.17
    zell
    0.16
    _T
    0.16
    ilst
    0.16
    ÂŃt
    0.15
     íĭ°
    0.15
    _tc
    0.15
    illo
    0.15
    webs
    0.15
    Activations Density 0.067%

    No Known Activations