© 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. 7-LLAMASCOPE-RES-32K
    6. 6067
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate intention or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resi
    -0.17
    elian
    -0.15
    endi
    -0.15
    shan
    -0.15
    tsy
    -0.15
    umer
    -0.14
    uin
    -0.14
    iants
    -0.14
    /OR
    -0.14
    arian
    -0.13
    POSITIVE LOGITS
    ald
    0.16
    .ai
    0.16
     Schultz
    0.14
    ¢åįķ
    0.14
    @class
    0.14
     Psi
    0.13
    497
    0.13
     cái
    0.13
    APPER
    0.13
    mia
    0.13
    Activations Density 0.064%

    No Known Activations