© 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. 30-LLAMASCOPE-RES-32K
    11. 11053
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to freelance work and expectations in client relationships

    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
     <+
    -0.15
     kino
    -0.15
    ůst
    -0.14
    steen
    -0.14
     licensee
    -0.14
    .Subscribe
    -0.14
    rics
    -0.14
    ıb
    -0.14
    /operators
    -0.14
    .netty
    -0.13
    POSITIVE LOGITS
     freel
    0.38
     gig
    0.37
     Freel
    0.35
     gigs
    0.35
     freelance
    0.35
     freelancer
    0.33
     Gig
    0.32
    fre
    0.30
    Fre
    0.30
    _fre
    0.28
    Activations Density 0.034%

    No Known Activations