INDEX

Explanations

references to legislative measures or policies related to governmental actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rupa

-0.15

jak

-0.15

ecial

-0.14

.qml

-0.14

Cum

-0.14

endency

-0.14

rod

-0.13

eldon

-0.13

 Druid

-0.13

POSITIVE LOGITS

/terms

0.15

 Millennium

0.14

oftware

0.14

ãģ¤ãģ¶

0.14

oten

0.14

 controvers

0.14

ãģıãģł

0.14

ìĬ¤íħľ

0.13

_DETECT

0.13

MDB

0.13

Activations Density 0.053%

references to legislative measures or policies related to governmental actions

No Comments

No Known Activations