© 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. 30-LLAMASCOPE-RES-32K
    6. 5693
    Prev
    Next
    INDEX
    Explanations

    assertions about objects and their properties, particularly in relation to their impact or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jvu
    -0.16
    .hw
    -0.15
    ÑĪив
    -0.15
    amiliar
    -0.14
    oku
    -0.14
    UMB
    -0.13
     placement
    -0.13
    ule
    -0.13
     McKay
    -0.13
    aoke
    -0.13
    POSITIVE LOGITS
     shock
    0.29
     alarm
    0.26
     disappoint
    0.26
     refresh
    0.24
     disarm
    0.24
     anything
    0.24
     embarrass
    0.22
     envi
    0.22
     disgust
    0.22
     delight
    0.21
    Activations Density 0.422%

    No Known Activations