© 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. 2456
    Prev
    Next
    INDEX
    Explanations

    mentions of significant personal or relational changes

    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
    ureen
    -0.15
    ogens
    -0.14
    estro
    -0.14
    cts
    -0.14
    osi
    -0.14
    inine
    -0.14
    eeper
    -0.13
    upe
    -0.13
    723
    -0.13
    ilton
    -0.13
    POSITIVE LOGITS
     until
    0.91
    until
    0.84
     Until
    0.76
    Until
    0.73
    .until
    0.61
     hasta
    0.60
    _until
    0.59
     till
    0.58
     até
    0.56
     jusqu
    0.54
    Activations Density 0.223%

    No Known Activations