© 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. 19-LLAMASCOPE-RES-32K
    11. 2356
    Prev
    Next
    INDEX
    Explanations

    phrases related to defensive performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieri
    -0.16
    orch
    -0.16
    ENTE
    -0.15
    SCORE
    -0.15
    rze
    -0.15
    .xhtml
    -0.15
    ibbon
    -0.15
    меж
    -0.15
    нÑıÑĤи
    -0.14
    .Loader
    -0.14
    POSITIVE LOGITS
     security
    0.26
     defence
    0.25
     defense
    0.25
     defensive
    0.24
    éĺ²
    0.23
     Security
    0.22
     coverage
    0.21
     protection
    0.21
     Defensive
    0.21
    å®Ī
    0.20
    Activations Density 0.124%

    No Known Activations