© 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. 23-LLAMASCOPE-RES-32K
    11. 29426
    Prev
    Next
    INDEX
    Explanations

    references to body parts, particularly focusing on shoulders and knees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.16
    .uc
    -0.16
    (íģ¬ê¸°
    -0.15
    utut
    -0.15
    anford
    -0.15
    /Private
    -0.14
     hóa
    -0.14
    ecer
    -0.14
     Heb
    -0.14
    aney
    -0.14
    POSITIVE LOGITS
    -high
    0.23
    -length
    0.22
    /head
    0.21
    bone
    0.21
    /el
    0.20
    éĥ¨
    0.18
    /back
    0.18
     joint
    0.18
    bones
    0.18
    joint
    0.18
    Activations Density 0.051%

    No Known Activations