© 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. 25-LLAMASCOPE-RES-32K
    6. 10500
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nia
    -0.15
    ладÑĥ
    -0.15
    .fb
    -0.15
    etten
    -0.14
    chas
    -0.14
    ilha
    -0.14
    è¦
    -0.14
    گراÙĨ
    -0.14
    rovers
    -0.14
    Race
    -0.14
    POSITIVE LOGITS
    _FWD
    0.15
     Cum
    0.15
    oose
    0.13
    OSE
    0.13
    æ·
    0.13
     ADVISED
    0.13
     Trim
    0.13
    оÑĤÑĥ
    0.13
    MenuStrip
    0.13
     trim
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.