© 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. 6-LLAMASCOPE-RES-32K
    11. 28487
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and instructions related to procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dün
    -0.16
     wa
    -0.16
    760
    -0.15
    assy
    -0.15
    653
    -0.14
    oper
    -0.14
     Marr
    -0.14
    lish
    -0.14
     Thom
    -0.14
    obo
    -0.14
    POSITIVE LOGITS
    _PREVIEW
    0.14
    .struts
    0.14
    -thumbnail
    0.14
    ĮĢ
    0.14
     Penalty
    0.14
    zers
    0.14
    ãĥªãĥ¼ãĤº
    0.13
    arus
    0.13
    廳
    0.13
    enders
    0.13
    Activations Density 0.234%

    No Known Activations