© 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. 22950
    Prev
    Next
    INDEX
    Explanations

    expressions of strong excitement or anticipation

    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
    olor
    -0.15
    .vendor
    -0.15
    undi
    -0.14
    JKLM
    -0.14
    ugh
    -0.14
    aby
    -0.14
     Crowley
    -0.14
    çħ¤
    -0.13
    asa
    -0.13
    LAG
    -0.13
    POSITIVE LOGITS
     pumped
    0.38
     excited
    0.37
    exc
    0.35
    -exc
    0.35
     excit
    0.35
     Exc
    0.34
     exited
    0.32
    Exc
    0.32
     Pump
    0.32
     excitement
    0.31
    Activations Density 0.100%

    No Known Activations