INDEX

Explanations

the word "or" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ku

-0.19

eria

-0.16

lev

-0.16

OLUME

-0.15

bart

-0.15

kus

-0.15

bla

-0.15

mj

-0.15

å°¾

-0.15

ilo

-0.14

POSITIVE LOGITS

shan

0.17

shal

0.15

acular

0.15

à¥įà¤¸à¤°

0.14

ignet

0.14

ought

0.14

ëŁ´

0.14

à¤Ĺà¤²

0.14

/bower

0.14

Activations Density 0.017%

the word "or" in various contexts

No Comments

No Known Activations