© 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. 18637
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate trust or reliance on the speaker's credibility

    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
    wap
    -0.16
     mens
    -0.15
    akra
    -0.15
    wan
    -0.15
     may
    -0.14
    aqu
    -0.14
    [System
    -0.14
    íĥģ
    -0.14
    atform
    -0.14
    quist
    -0.14
    POSITIVE LOGITS
    engkap
    0.19
    ONGL
    0.17
     none
    0.16
    .Solid
    0.15
     contrary
    0.15
    enaire
    0.15
    oven
    0.15
    CLU
    0.15
    ermann
    0.14
    _cmos
    0.14
    Activations Density 0.029%

    No Known Activations