INDEX

Explanations

references to book reviews and related bibliographic data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

rÃ³

-0.16

 decentral

-0.15

Å¯st

-0.14

 Greatest

-0.14

rees

-0.14

ÏģÎµ

-0.14

nia

-0.13

icas

-0.13

idar

-0.13

alar

-0.13

POSITIVE LOGITS

DEX

0.16

 ï¿¥

0.15

evenodd

0.15

Exit

0.15

ingers

0.15

ÑħÐ¾Ð²Ð¸

0.15

enie

0.15

cliffe

0.14

/movie

0.14

opsis

0.14

Activations Density 0.040%

references to book reviews and related bibliographic data

No Comments

No Known Activations