© 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. 27-LLAMASCOPE-RES-32K
    6. 487
    Prev
    Next
    INDEX
    Explanations

    Java annotations and related programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.18
    usercontent
    -0.15
    emek
    -0.15
    ChangedEventArgs
    -0.15
     Alejandro
    -0.15
    busters
    -0.14
    ynch
    -0.14
    cripts
    -0.14
    ODE
    -0.14
    .hl
    -0.14
    POSITIVE LOGITS
     annotation
    0.33
    annotation
    0.31
    .annotation
    0.30
     annotations
    0.29
     annot
    0.27
     Annotation
    0.27
    Retention
    0.27
     ann
    0.26
    _annotation
    0.26
    Annotation
    0.26
    Activations Density 0.057%

    No Known Activations