© 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. 20-LLAMASCOPE-RES-32K
    11. 27355
    Prev
    Next
    INDEX
    Explanations

    instances of the word "last" and related phrases indicating endings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     näch
    -0.15
    abajo
    -0.15
    .vs
    -0.15
    vsp
    -0.14
    coles
    -0.14
     nächsten
    -0.14
    æľĢæĸ°
    -0.14
    ãģĵãĤĵ
    -0.14
    084
    -0.14
    (ARG
    -0.13
    POSITIVE LOGITS
     before
    0.29
     remaining
    0.25
    remaining
    0.23
    before
    0.23
    -before
    0.23
     Before
    0.23
    _before
    0.21
     gas
    0.21
    Before
    0.20
    _BEFORE
    0.20
    Activations Density 0.089%

    No Known Activations