© 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. 30-LLAMASCOPE-RES-32K
    6. 10968
    Prev
    Next
    INDEX
    Explanations

    directives and conditional phrases relating to tasks or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    393
    -0.16
    posed
    -0.15
    ested
    -0.15
    erp
    -0.13
     Vor
    -0.13
    ëij¥
    -0.13
    mere
    -0.13
     =
    -0.13
    loe
    -0.13
    Äĥr
    -0.13
    POSITIVE LOGITS
    -power
    0.17
     throne
    0.17
    aida
    0.15
    LEAN
    0.15
    855
    0.14
    unger
    0.14
    odge
    0.14
    lean
    0.14
     اختÛĮار
    0.14
    OOM
    0.14
    Activations Density 0.009%

    No Known Activations