© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 18381
    Prev
    Next
    INDEX
    Explanations

    terms related to music tracks and their structure in albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ört
    -0.14
     Äįásti
    -0.13
    assen
    -0.13
    нии
    -0.12
    ottes
    -0.12
    quo
    -0.12
     nevy
    -0.11
    otto
    -0.11
     ëĭ¤ìĭľ
    -0.11
     kısm
    -0.11
    POSITIVE LOGITS
     per
    0.75
     each
    0.52
     EACH
    0.44
    per
    0.42
     ap
    0.42
     total
    0.41
    _per
    0.41
    each
    0.39
     maximum
    0.39
     PER
    0.38
    Activations Density 0.277%

    No Known Activations