© 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. 30-LLAMASCOPE-RES-32K
    6. 18365
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations related to people, organizations, and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Formatter
    -0.17
    .ManyToMany
    -0.17
    .RequestMethod
    -0.15
    .ObjectModel
    -0.15
    .ActionListener
    -0.14
    .DropDown
    -0.14
     and
    -0.14
    .HorizontalAlignment
    -0.13
    .Formatting
    -0.13
    .apiUrl
    -0.13
    POSITIVE LOGITS
    .
    0.63
    .,
    0.52
    .:
    0.48
    ./
    0.46
    .;
    0.43
    .-
    0.42
    .),
    0.42
    .).
    0.39
    .).↵↵
    0.37
    .=
    0.37
    Activations Density 1.046%

    No Known Activations