INDEX

Explanations

punctuation and sentence-ending markers 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ná»¯a

-0.16

æĬľ

-0.15

 yourselves

-0.15

ookie

-0.15

irection

-0.14

.AWS

-0.13

 Yours

-0.13

.RunWith

-0.13

OwnProperty

-0.13

read

-0.13

POSITIVE LOGITS

 hearing

0.20

 Hearing

0.19

keh

0.17

 however

0.17

Eh

0.17

 However

0.16

ordo

0.16

 moreover

0.15

Moreover

0.15

 Thinking

0.15

Activations Density 0.025%

punctuation and sentence-ending markers in the text

No Comments

No Known Activations