© 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. 25-LLAMASCOPE-RES-32K
    11. 17135
    Prev
    Next
    INDEX
    Explanations

    references to uncovering hidden truths or secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åѤ
    -0.15
    ë´ī
    -0.15
    å¡ļ
    -0.15
    acus
    -0.14
    çī¹èī²
    -0.14
    ÎŃÏģγ
    -0.14
    æŀĿ
    -0.13
    ronic
    -0.13
    itten
    -0.13
    Chance
    -0.13
    POSITIVE LOGITS
     truth
    0.64
    truth
    0.52
     Truth
    0.50
     truths
    0.49
     secrets
    0.49
     true
    0.48
    Truth
    0.45
     verdad
    0.41
     secret
    0.41
    true
    0.38
    Activations Density 0.226%

    No Known Activations