© 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. 19-LLAMASCOPE-RES-32K
    11. 6280
    Prev
    Next
    INDEX
    Explanations

    discussions about moral and ethical dilemmas in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rather
    -0.25
    vier
    -0.16
     somewhat
    -0.15
     sogar
    -0.15
    aze
    -0.15
    rather
    -0.15
     plutôt
    -0.15
     repet
    -0.14
     repetitive
    -0.14
    åıĪ
    -0.14
    POSITIVE LOGITS
     suddenly
    0.23
     nor
    0.19
     sudden
    0.18
     necessarily
    0.17
    nor
    0.16
     randomly
    0.15
    llx
    0.15
     rocket
    0.15
     overnight
    0.15
     Suddenly
    0.15
    Activations Density 0.302%

    No Known Activations