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. 12-LLAMASCOPE-RES-32K
    6. 5993
    Prev
    Next
    INDEX
    Explanations

    numerical scales and ranking systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roat
    -0.17
    ely
    -0.16
    isse
    -0.15
     Naz
    -0.15
    976
    -0.15
    avez
    -0.14
     Retro
    -0.14
    prung
    -0.14
    ot
    -0.14
     Gir
    -0.14
    POSITIVE LOGITS
    ÐĶÐļ
    0.18
    ίÏĥ
    0.16
    .scalablytyped
    0.15
    -NLS
    0.15
    ãĥ¼ãĥģ
    0.15
    DBObject
    0.15
    olan
    0.14
    ा:
    0.14
     smr
    0.14
     бÑĥдÑĤо
    0.14
    Activations Density 0.072%

    No Known Activations