Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 22500
    Prev
    Next
    INDEX
    Explanations

    references to fraudulent activities and legal allegations in financial contexts

    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
    acco
    -0.19
    apus
    -0.15
    robat
    -0.14
    ä¸Ī
    -0.14
     publicity
    -0.14
    Undefined
    -0.14
     wakeup
    -0.14
    byname
    -0.14
     Interpret
    -0.13
     announc
    -0.13
    POSITIVE LOGITS
     cons
    0.22
     coll
    0.22
     fun
    0.21
     improperly
    0.20
    fun
    0.18
     tam
    0.18
     schem
    0.18
     pressures
    0.18
     launder
    0.18
     mish
    0.17
    Activations Density 0.243%

    No Known Activations