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. 4-LLAMASCOPE-RES-32K
    6. 14541
    Prev
    Next
    INDEX
    Explanations

    phrases indicating long-standing feelings or desires

    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
    WO
    -0.18
    aktu
    -0.17
     Red
    -0.16
    ieux
    -0.15
    insi
    -0.15
     Ment
    -0.15
     Merry
    -0.15
     USDA
    -0.15
    ilis
    -0.14
     Ze
    -0.14
    POSITIVE LOGITS
    RYPT
    0.17
    ÅĻen
    0.15
    elt
    0.15
    رÙĪØ¯
    0.15
    andır
    0.14
    aland
    0.14
    vae
    0.14
    Ãły
    0.14
    ãģ¼
    0.14
    ãĥĥãĥĪ
    0.14
    Activations Density 0.247%

    No Known Activations