© 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. 4999
    Prev
    Next
    INDEX
    Explanations

    references to body parts, particularly those associated with the shoulder and knee

    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
    ediator
    -0.17
     fund
    -0.15
    .uc
    -0.15
     hóa
    -0.14
    utut
    -0.14
    _GC
    -0.13
     ApiController
    -0.13
    spell
    -0.13
    ovah
    -0.13
    anford
    -0.13
    POSITIVE LOGITS
    -high
    0.24
    -length
    0.24
    bone
    0.20
    -height
    0.20
    /back
    0.20
    /el
    0.20
    éĥ¨
    0.19
    /head
    0.19
    joint
    0.19
     joint
    0.19
    Activations Density 0.045%

    No Known Activations