© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 15383
    Prev
    Next
    INDEX
    Explanations

    phrases related to restarting or beginning anew

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azzi
    -0.17
    asar
    -0.15
    pekt
    -0.14
    eking
    -0.14
     continuing
    -0.14
    heim
    -0.14
     continued
    -0.14
    105
    -0.14
    izons
    -0.14
     Schro
    -0.14
    POSITIVE LOGITS
     again
    0.55
    again
    0.49
     Again
    0.47
     lại
    0.46
    Again
    0.45
    _again
    0.39
    AGAIN
    0.35
     novamente
    0.35
     wieder
    0.33
     AGAIN
    0.32
    Activations Density 0.071%

    No Known Activations