© 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. 17-LLAMASCOPE-RES-32K
    11. 31775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating near certainties or approximations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ró
    -0.17
    oldem
    -0.16
    iÄĻ
    -0.16
    emmel
    -0.15
    ãĥ¥
    -0.15
     absolutely
    -0.15
    etro
    -0.14
     ÙĪاس
    -0.14
    iare
    -0.14
    ilis
    -0.14
    POSITIVE LOGITS
    ument
    0.19
    ived
    0.15
    sense
    0.15
    afari
    0.15
    nr
    0.15
    lassian
    0.14
    _almost
    0.14
    .Toolkit
    0.14
     exclusively
    0.14
    n
    0.14
    Activations Density 0.022%

    No Known Activations