INDEX

Explanations

instances of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Å¼e

-0.15

Î´ÎŃ

-0.15

agar

-0.14

 Beled

-0.14

æ®Ĭ

-0.14

itled

-0.14

bat

-0.14

åĲ¹

-0.14

ction

-0.13

trs

-0.13

POSITIVE LOGITS

YM

0.19

iox

0.16

 skins

0.15

 fondo

0.15

assa

0.15

 tatto

0.15

CLUDING

0.14

 Strait

0.14

readcr

0.14

Vul

0.14

Activations Density 0.020%

instances of the word "on."

No Comments

No Known Activations