INDEX

Explanations

punctuation marks and format-related characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

abay

-0.16

ument

-0.16

onom

-0.16

foy

-0.15

 Bull

-0.15

alus

-0.14

poster

-0.14

ion

-0.14

itemap

-0.14

onga

-0.14

POSITIVE LOGITS

pl

0.14

relude

0.14

ç°

0.14

acher

0.14

 Abel

0.14

.students

0.14

iddy

0.14

 Sext

0.13

_rc

0.13

Activations Density 0.043%

punctuation marks and format-related characters

No Comments

No Known Activations