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. 23463
    Prev
    Next
    INDEX
    Explanations

    terms and metrics related to crude oil

    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
    oho
    -0.16
    odyn
    -0.16
    psilon
    -0.15
    rient
    -0.14
    iento
    -0.14
     دست
    -0.14
    ITES
    -0.14
    olia
    -0.14
    rych
    -0.14
    thy
    -0.14
    POSITIVE LOGITS
     asphalt
    0.29
     dist
    0.26
     fractions
    0.25
     arom
    0.25
     pitches
    0.23
     fraction
    0.23
     cracking
    0.23
     aromatic
    0.23
     pitch
    0.22
     Fra
    0.22
    Activations Density 0.015%

    No Known Activations