INDEX

Explanations

notable punctuation and narrative transitions

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

Not in Any Lists

No Comments

Negative Logits

yen

-0.17

hte

-0.14

åį´

-0.14

persons

-0.14

 however

-0.14

nga

-0.14

åı¯æĺ¯

-0.14

 Pussy

-0.13

ÑĢÐ°Ñĩ

-0.13

_dd

-0.13

POSITIVE LOGITS

"[

0.20

 “[

0.18

ICY

0.16

"[

0.16

Thumbnail

0.15

zia

0.15

 alongside

0.15

 SPDX

0.15

 Advertisement

0.14

Activations Density 0.278%

notable punctuation and narrative transitions

No Comments

No Known Activations