© 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. 27-LLAMASCOPE-RES-32K
    11. 10908
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate attributes or descriptions related to quality and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    438
    -0.15
    ingham
    -0.15
    eward
    -0.13
    æĬķ注
    -0.12
    ennes
    -0.12
    623
    -0.12
    ’n
    -0.12
    ÑĨен
    -0.12
    anyahu
    -0.12
    uppet
    -0.12
    POSITIVE LOGITS
    pcl
    0.15
    -Sah
    0.13
    WRAPPER
    0.13
     StringComparison
    0.13
    lili
    0.12
    .shows
    0.12
    elere
    0.12
    )((((
    0.12
    ladu
    0.12
    .synthetic
    0.12
    Activations Density 0.148%

    No Known Activations