Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 24274
    Prev
    Next
    INDEX
    Explanations

    instructions related to manual input and document editing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æk
    -0.15
     Laden
    -0.15
    ona
    -0.14
    они
    -0.14
    rust
    -0.14
    defer
    -0.14
    _SHADOW
    -0.14
     overnight
    -0.14
    ASA
    -0.14
    abbr
    -0.13
    POSITIVE LOGITS
     manually
    0.42
     manual
    0.41
     Manual
    0.33
    Manual
    0.32
    manual
    0.31
     MANUAL
    0.31
    _manual
    0.30
     explicit
    0.30
     explicitly
    0.30
    explicit
    0.29
    Activations Density 0.122%

    No Known Activations