INDEX

Explanations

dates and references to specific events or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Halloween

-0.17

 Christmas

-0.16

 Sept

-0.16

 Winter

-0.15

 christmas

-0.15

cient

-0.15

åĨ¬

-0.15

Oct

-0.15

ateg

-0.14

oct

-0.14

POSITIVE LOGITS

May

0.24

May

0.23

ilinear

0.17

amoto

0.17

June

0.16

nard

0.16

-May

0.16

procs

0.16

erk

0.15

oral

0.15

Activations Density 0.028%

dates and references to specific events or time periods

No Comments

No Known Activations