© 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. 24-LLAMASCOPE-RES-32K
    11. 15583
    Prev
    Next
    INDEX
    Explanations

    the letter 'G' in various forms throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    олов
    -0.21
    AME
    -0.17
    uru
    -0.17
    avin
    -0.16
    arden
    -0.16
    IVEN
    -0.16
    ames
    -0.15
    apult
    -0.15
     vým
    -0.15
    itious
    -0.15
    POSITIVE LOGITS
    erge
    0.16
    isors
    0.16
    uters
    0.14
     weekly
    0.14
     apparent
    0.14
    SELL
    0.14
    è³Ģ
    0.14
    idebar
    0.14
    ål
    0.14
    izens
    0.14
    Activations Density 0.060%

    No Known Activations