© 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. 15-LLAMASCOPE-RES-32K
    11. 26171
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Roger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kah
    -0.17
    posables
    -0.16
    úsqueda
    -0.15
     crossorigin
    -0.15
    ively
    -0.15
    meden
    -0.15
    бÑĥ
    -0.15
    .SC
    -0.15
    ibase
    -0.15
    HING
    -0.14
    POSITIVE LOGITS
    yclic
    0.15
    ãģ¾ãģŁ
    0.15
    ism
    0.14
    erator
    0.14
    als
    0.14
    uity
    0.14
    esti
    0.14
    anco
    0.14
    yz
    0.14
    zar
    0.14
    Activations Density 0.058%

    No Known Activations