© 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. 6792
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and the concept of collaboration

    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
    λÎŃον
    -0.13
    ãģ°ãģĭãĤĬ
    -0.13
     useClass
    -0.12
    âĶIJ
    -0.12
    inherits
    -0.11
    utilus
    -0.11
     Both
    -0.11
     simplest
    -0.11
    hausen
    -0.10
    UILTIN
    -0.10
    POSITIVE LOGITS
     other
    1.41
    other
    1.12
     others
    1.10
    åħ¶ä»ĸ
    1.04
     OTHER
    1.00
     autres
    0.97
     Other
    0.96
    Other
    0.94
     anderen
    0.94
    -other
    0.94
    Activations Density 3.406%

    No Known Activations