INDEX

Explanations

phrases indicating location or reference points within a text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

umat

-0.16

EDA

-0.15

unds

-0.15

ride

-0.14

pany

-0.14

oine

-0.14

Ð½Ð¸ÑĤ

-0.14

urg

-0.14

.struct

-0.14

oire

-0.14

POSITIVE LOGITS

ieder

0.18

inger

0.16

Leap

0.15

ynom

0.14

åįĪ

0.14

TOTYPE

0.14

aghan

0.14

Î´ÎµÎ¹

0.14

 Leap

0.14

Activations Density 0.021%

phrases indicating location or reference points within a text

No Comments

No Known Activations