© 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. 15-LLAMASCOPE-RES-32K
    6. 24811
    Prev
    Next
    INDEX
    Explanations

    numerical values and version information related to software components

    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
    ãģİ
    -0.15
     æ¥Ń
    -0.15
     -:-
    -0.14
    alcon
    -0.14
    aticon
    -0.14
    urd
    -0.14
    .GridView
    -0.14
    oksen
    -0.14
     aside
    -0.13
    UNUSED
    -0.13
    POSITIVE LOGITS
     stoi
    0.15
    rc
    0.15
    gne
    0.15
    _RC
    0.15
    .x
    0.15
    .X
    0.14
     http
    0.14
    é£İ
    0.14
    http
    0.13
    $self
    0.13
    Activations Density 0.034%

    No Known Activations