© 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. 28-LLAMASCOPE-RES-32K
    11. 239
    Prev
    Next
    INDEX
    Explanations

    mentions of software applications and related technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /inet
    -0.13
    xde
    -0.13
    λαν
    -0.13
    ãģıãĤĮ
    -0.13
    íķĢ
    -0.13
    QUIRED
    -0.12
    chez
    -0.12
    ange
    -0.12
     ÙħØ«
    -0.12
    ledik
    -0.12
    POSITIVE LOGITS
     called
    1.46
    called
    1.25
     Called
    1.21
    Called
    1.09
    åı«
    0.97
    -called
    0.93
     llam
    0.91
     termed
    0.80
    称
    0.79
    _called
    0.77
    Activations Density 1.611%

    No Known Activations