© 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. 18-LLAMASCOPE-RES-32K
    11. 28448
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals associated with various contributions or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aos
    -0.14
     awakeFromNib
    -0.14
    fte
    -0.13
    asca
    -0.13
     Exodus
    -0.13
    opot
    -0.13
     cuck
    -0.13
     swell
    -0.13
    pose
    -0.13
    dit
    -0.13
    POSITIVE LOGITS
     Foundation
    0.20
     foundation
    0.17
    .scalablytyped
    0.17
     FOUND
    0.17
    foundation
    0.16
     Sculpt
    0.15
    Foundation
    0.15
     Memorial
    0.14
    Seat
    0.14
     Mellon
    0.14
    Activations Density 0.168%

    No Known Activations