INDEX

Explanations

elements related to figures, captions, and graphical representations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

emin

-0.16

 bere

-0.16

_DUMP

-0.15

inking

-0.15

resh

-0.14

/***/

-0.14

ember

-0.14

ibir

-0.14

oline

-0.14

 Peoples

-0.14

POSITIVE LOGITS

 NONINFRINGEMENT

0.17

hq

0.14

dddd

0.14

ĥn

0.14

IDES

0.14

 Blasio

0.14

 stamps

0.14

otos

0.13

agged

0.13

fold

0.13

Activations Density 0.047%

elements related to figures, captions, and graphical representations in the text

No Comments

No Known Activations