© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    references to recognition, support, and evidence in various contexts

    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
    омен
    -0.16
    ugg
    -0.16
    _requires
    -0.16
     McCabe
    -0.16
    iggins
    -0.15
    olumn
    -0.15
    agr
    -0.15
    eyer
    -0.15
    .isConnected
    -0.15
    CDATA
    -0.15
    POSITIVE LOGITS
     via
    0.36
     form
    0.36
     consisting
    0.33
     consist
    0.31
    via
    0.31
     forms
    0.28
     consisted
    0.27
     consists
    0.27
     Via
    0.25
     виде
    0.25
    Activations Density 0.265%

    No Known Activations