INDEX

Explanations

elements related to writing and composition techniques

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

achi

-0.19

ernote

-0.17

ErrorException

-0.17

endet

-0.16

ÑĤÐ°Ð±

-0.15

rias

-0.15

Dat

-0.15

smouth

-0.14

à¥įà¤ł

-0.14

iage

-0.14

POSITIVE LOGITS

ott

0.16

 Huck

0.16

ske

0.15

nam

0.15

 Sabb

0.14

Ð·Ð²

0.14

rant

0.13

oldur

0.13

irit

0.13

edef

0.13

Activations Density 0.009%

elements related to writing and composition techniques

No Known Activations