© 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. 9-LLAMASCOPE-RES-32K
    11. 6600
    Prev
    Next
    INDEX
    Explanations

    the presence of high-impact nouns and verbs related to emotional or situational stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ°
    -0.15
     cor
    -0.15
     literature
    -0.15
    _CBC
    -0.15
    ector
    -0.14
     Holl
    -0.14
    entral
    -0.14
     ÛĮاÙģت
    -0.14
     central
    -0.14
    á»
    -0.14
    POSITIVE LOGITS
     Magnus
    0.16
    enum
    0.16
     Canc
    0.15
    psc
    0.14
    102
    0.14
    quam
    0.14
    oly
    0.14
    294
    0.14
    åĭ
    0.14
    èĮ
    0.13
    Activations Density 0.011%

    No Known Activations