INDEX

Explanations

punctuation marks and commonly used connecting words in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

orda

-0.17

oa

-0.15

rou

-0.15

æŃ

-0.15

.dispatchEvent

-0.14

_kb

-0.14

ype

-0.14

ilar

-0.14

å¨ľ

-0.14

 phÃ³ng

-0.14

POSITIVE LOGITS

urdy

0.16

ibold

0.16

resher

0.15

åº

0.15

 tele

0.15

 otherwise

0.14

Kab

0.14

omorphic

0.14

asca

0.14

Rt

0.14

Activations Density 0.005%

punctuation marks and commonly used connecting words in the text

No Comments

No Known Activations