© 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. 18-LLAMASCOPE-RES-32K
    6. 6482
    Prev
    Next
    INDEX
    Explanations

    elements related to music albums and their characteristics

    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
    AMA
    -0.16
    Misc
    -0.15
    roc
    -0.15
    é¢ĺ
    -0.14
    oster
    -0.14
    misc
    -0.14
    _misc
    -0.14
    manuel
    -0.14
     Born
    -0.14
    ass
    -0.14
    POSITIVE LOGITS
     version
    0.71
     versions
    0.63
     Version
    0.57
    çīĪæľ¬
    0.57
    version
    0.56
     VERSION
    0.53
    -version
    0.52
     Versions
    0.52
    Version
    0.52
     versión
    0.51
    Activations Density 0.269%

    No Known Activations