© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 24839
    Prev
    Next
    INDEX
    Explanations

    phrases indicating engagement and intrigue in storytelling or creative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    378
    -0.18
    venir
    -0.16
    оÑģÑĤ
    -0.16
    373
    -0.16
    stk
    -0.15
    ulton
    -0.15
    ost
    -0.15
    PickerController
    -0.15
    377
    -0.14
    ITHER
    -0.14
    POSITIVE LOGITS
    alar
    0.15
     æķħ
    0.15
     Vital
    0.15
    ìĿ´ìķ¼
    0.14
    naments
    0.14
    ornment
    0.14
    aris
    0.14
    onom
    0.14
     bais
    0.14
     vitae
    0.13
    Activations Density 0.189%

    No Known Activations