Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-LLAMASCOPE-RES-32K
    6. 11884
    Prev
    Next
    INDEX
    Explanations

    references to David Bowie and his music-related elements or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lee
    -0.16
    oll
    -0.15
     æº
    -0.15
     Kling
    -0.14
     Carb
    -0.14
    CCI
    -0.14
    ÙĦØ·
    -0.14
    fi
    -0.14
    INVAL
    -0.14
    inkel
    -0.14
    POSITIVE LOGITS
    ousel
    0.16
    atif
    0.14
    ihn
    0.14
    createFrom
    0.14
    orden
    0.14
    ift
    0.14
    chemes
    0.14
    Łèĥ½
    0.14
    cheme
    0.14
     Shift
    0.14
    Activations Density 0.005%

    No Known Activations