INDEX

Explanations

numerical identifiers, possibly related to references or specifications

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

gren

-0.16

adel

-0.16

/libs

-0.14

ValuePair

-0.14

 fortunes

-0.14

åĪĩ

-0.14

\Catalog

-0.14

/Dk

-0.14

-0.13

KeyValuePair

-0.13

POSITIVE LOGITS

Sink

0.16

ÃĹ↵↵

0.16

umm

0.15

REV

0.14

rays

0.14

Lead

0.14

 explor

0.14

 èµ·

0.14

Unified

0.14

Î¼ÏĨ

0.14

Activations Density 0.132%

numerical identifiers, possibly related to references or specifications

No Known Activations