© 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. 22-LLAMASCOPE-RES-32K
    11. 28066
    Prev
    Next
    INDEX
    Explanations

    mentions of brands and their associated controversies or defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ziej
    -0.15
    åĤ¬
    -0.15
    ustos
    -0.14
    RenderTarget
    -0.13
    ÂŁ
    -0.13
    gré
    -0.13
    tica
    -0.13
    unger
    -0.13
    ruk
    -0.13
    Enlarge
    -0.13
    POSITIVE LOGITS
     defense
    0.57
     defence
    0.54
     defend
    0.52
     defended
    0.49
     defends
    0.47
     defending
    0.47
    -defense
    0.47
    defense
    0.46
     defenses
    0.46
     defensive
    0.45
    Activations Density 0.398%

    No Known Activations