INDEX

Explanations

instances of the word "Earlier," indicating a focus on time-related references in the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

hai

-0.17

undles

-0.16

iams

-0.15

isphere

-0.15

CHE

-0.15

iaux

-0.15

 yans

-0.14

Łèĥ½

-0.14

 Chew

-0.14

tÃ©

-0.14

POSITIVE LOGITS

çł

0.18

 Minh

0.16

 simplex

0.16

å¿

0.15

ãĥ³ãĥĲãĥ¼

0.15

 cres

0.14

 pooled

0.14

/latest

0.13

Ã¼ven

0.13

illon

0.13

Activations Density 0.006%

instances of the word "Earlier," indicating a focus on time-related references in the content

No Comments

No Known Activations