© 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. 18-LLAMASCOPE-RES-32K
    11. 27855
    Prev
    Next
    INDEX
    Explanations

    references to events and their organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alte
    -0.15
    regon
    -0.14
    uft
    -0.14
    vÄĽ
    -0.14
    nage
    -0.13
     maç
    -0.13
    _IOCTL
    -0.13
    OPY
    -0.13
     Clips
    -0.13
    visa
    -0.13
    POSITIVE LOGITS
     happening
    0.40
     occurring
    0.35
     happened
    0.33
     diá»ħn
    0.33
     happens
    0.33
     held
    0.32
    åıijçĶŁ
    0.31
     happen
    0.30
     occurs
    0.30
     occurred
    0.29
    Activations Density 0.127%

    No Known Activations