INDEX

Explanations

instances of the word "right" in various contexts

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

heim

-0.17

keley

-0.17

lical

-0.16

agus

-0.15

uke

-0.15

quential

-0.15

ilder

-0.15

agy

-0.15

ukes

-0.14

azed

-0.14

POSITIVE LOGITS

noe

0.18

ow

0.18

nw

0.17

now

0.17

row

0.17

 moment

0.17

nao

0.16

no

0.15

 away

0.15

 ÑģÐµÐ¹ÑĩÐ°Ñģ

0.15

Activations Density 0.007%

instances of the word "right" in various contexts

No Comments

No Known Activations