© 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. 20-LLAMASCOPE-RES-32K
    11. 26439
    Prev
    Next
    INDEX
    Explanations

    concepts related to stages and processes, particularly in development and lifecycle contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oster
    -0.14
    gain
    -0.14
    bow
    -0.14
    resh
    -0.14
     Mast
    -0.14
    acad
    -0.14
    _arm
    -0.13
    oldem
    -0.13
    ML
    -0.13
    InBackground
    -0.13
    POSITIVE LOGITS
     stages
    0.74
     stage
    0.71
     Stage
    0.63
    Stage
    0.59
    stage
    0.58
    -stage
    0.57
    _stage
    0.55
    éĺ¶æ®µ
    0.52
    (stage
    0.52
    .stage
    0.50
    Activations Density 0.166%

    No Known Activations