© 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. 13-LLAMASCOPE-RES-32K
    11. 16806
    Prev
    Next
    INDEX
    Explanations

    descriptions of lively and attractive places or scenes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahi
    -0.16
    eor
    -0.14
    ould
    -0.14
    raith
    -0.14
     seins
    -0.14
    ез
    -0.14
    Ñģм
    -0.13
     FindObjectOfType
    -0.13
     ÐłÐ¾ÑģÑģийÑģкой
    -0.13
    Consum
    -0.13
    POSITIVE LOGITS
    ecz
    0.14
     hosts
    0.14
     Transparent
    0.14
     land
    0.14
    _defs
    0.13
     à¹Ģà¸Ĥà¸ķ
    0.13
    _WAKE
    0.13
    UIView
    0.13
    authenticate
    0.13
     beta
    0.13
    Activations Density 0.267%

    No Known Activations