© 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. 24999
    Prev
    Next
    INDEX
    Explanations

    instances of character names and specific identifiers associated with cultural references

    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
    Symbols
    -0.14
    xCC
    -0.14
    aida
    -0.14
     ÑĤоÑĢ
    -0.14
    à¹Ĥà¸Ĺ
    -0.14
    ´Ī
    -0.14
    antry
    -0.14
    /tool
    -0.13
     Tmax
    -0.13
    гл
    -0.13
    POSITIVE LOGITS
     meaning
    0.31
     translated
    0.30
     literally
    0.28
    meaning
    0.27
    liter
    0.25
    translated
    0.25
     translates
    0.24
    rough
    0.23
     Meaning
    0.23
     means
    0.23
    Activations Density 0.139%

    No Known Activations