© 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. 5620
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to groups or categories, particularly indicated by the word "these."

    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
    dest
    -0.15
    ìłģ
    -0.15
     dest
    -0.15
    ailability
    -0.14
    rol
    -0.14
     αÏħÏĦή
    -0.14
    ation
    -0.14
    Ë
    -0.14
    ener
    -0.13
    iveau
    -0.13
    POSITIVE LOGITS
    curity
    0.31
     same
    0.31
    quence
    0.30
     latter
    0.28
     kinds
    0.26
     sorts
    0.25
    cond
    0.25
    verity
    0.24
     days
    0.23
     guys
    0.23
    Activations Density 0.116%

    No Known Activations