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. 11-LLAMASCOPE-RES-32K
    6. 7250
    Prev
    Next
    INDEX
    Explanations

    references to outdoor activities and spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chers
    -0.15
    amodel
    -0.15
    aur
    -0.15
    chin
    -0.15
    udoku
    -0.15
    ching
    -0.14
    cher
    -0.14
    ฤ
    -0.14
    AxisAlignment
    -0.14
    uras
    -0.14
    POSITIVE LOGITS
    /out
    0.20
    /off
    0.18
    /in
    0.16
    abay
    0.15
    ward
    0.15
    wards
    0.15
    ject
    0.15
    apia
    0.15
    467
    0.14
    /open
    0.14
    Activations Density 0.019%

    No Known Activations