INDEX

Explanations

examples and references to questions or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ã¡la

-0.18

spender

-0.17

Ã¡ng

-0.16

 Ð´Ð¾ÑģÑĤ

-0.15

BS

-0.14

ukan

-0.13

 ACTION

-0.13

rodu

-0.13

simp

-0.13

ÃŃst

-0.13

POSITIVE LOGITS

 geme

0.16

ogl

0.14

oron

0.14

 Watkins

0.14

 tertiary

0.14

iek

0.14

_UNDEFINED

0.14

adir

0.14

 INTERRUPTION

0.13

DDR

0.13

Activations Density 0.058%

examples and references to questions or clarifications

No Comments

No Known Activations