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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 14360
    Prev
    Next
    INDEX
    Explanations

    references to bells and related musical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¬ãĥĵ
    -0.14
    assin
    -0.14
    tright
    -0.14
     Ballet
    -0.14
     cigaret
    -0.14
    upo
    -0.14
     Brewer
    -0.14
    enate
    -0.13
     combust
    -0.13
    nite
    -0.13
    POSITIVE LOGITS
     bell
    0.56
     bells
    0.53
    bell
    0.47
     ring
    0.46
     Bell
    0.46
    Bell
    0.45
     ringing
    0.43
     Ring
    0.42
     rings
    0.41
    Ring
    0.38
    Activations Density 0.025%

    No Known Activations