Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 4801
    Prev
    Next
    INDEX
    Explanations

    concepts related to control and restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omu
    -0.17
    lub
    -0.17
    ieves
    -0.16
    obe
    -0.16
    rupa
    -0.15
    -animate
    -0.15
    Specifier
    -0.14
    itura
    -0.14
    ibir
    -0.14
    oken
    -0.14
    POSITIVE LOGITS
    /control
    0.15
    ä½ı
    0.14
    ÅĻe
    0.14
    å°º
    0.14
     Shot
    0.14
     Wander
    0.14
    à¸Ľà¸£
    0.14
    CRET
    0.14
    erral
    0.13
    kt
    0.13
    Activations Density 0.103%

    No Known Activations