INDEX

Explanations

proper nouns and punctuation marks commonly associated with formal documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

zed

-0.16

nad

-0.15

inction

-0.14

Æ¡

-0.14

Ã¨mes

-0.14

.Css

-0.14

Margins

-0.14

ordo

-0.13

nie

-0.13

ograd

-0.13

POSITIVE LOGITS

ÙĨØ³

0.15

ãĥ§

0.14

 flagged

0.14

uges

0.14

rip

0.14

avian

0.14

 Holmes

0.14

vents

0.14

0.13

Activations Density 0.070%

proper nouns and punctuation marks commonly associated with formal documents

No Comments

No Known Activations