© 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. 24535
    Prev
    Next
    INDEX
    Explanations

    references to the Ramayana epic and related cultural or religious themes

    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
    an
    -1.38
    anou
    -0.58
    anja
    -0.57
    anik
    -0.56
    anova
    -0.55
    aná
    -0.54
    anje
    -0.53
    ané
    -0.51
    anlar
    -0.48
    anine
    -0.47
    POSITIVE LOGITS
    ans
    0.19
    ANS
    0.18
    ansk
    0.18
    ana
    0.17
    anship
    0.17
    anness
    0.17
    tank
    0.15
     Tank
    0.15
    Annotation
    0.15
    Tank
    0.15
    Activations Density 0.183%

    No Known Activations