© 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. 2-LLAMASCOPE-RES-32K
    11. 16446
    Prev
    Next
    INDEX
    Explanations

    instances of the word "opposite" and its related phrases or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jee
    -0.23
    ãģļ
    -0.15
    omite
    -0.15
     borderTop
    -0.15
    issa
    -0.15
     Territories
    -0.15
    owan
    -0.15
    iness
    -0.14
    PLEX
    -0.14
    ubi
    -0.14
    POSITIVE LOGITS
    eon
    0.17
    ANO
    0.15
    ano
    0.15
    ibu
    0.15
     comando
    0.14
     tesis
    0.14
    anno
    0.14
    eld
    0.14
    ellido
    0.13
    uant
    0.13
    Activations Density 0.011%

    No Known Activations