INDEX

Explanations

references to geographical directions or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Norte

-0.16

ename

-0.15

indows

-0.15

anders

-0.15

ëĵĿ

-0.14

Fixture

-0.14

ç¨

-0.14

OLUTION

-0.14

LF

-0.14

(typ

-0.14

POSITIVE LOGITS

side

0.23

 side

0.21

Side

0.19

 Side

0.19

bound

0.18

-side

0.17

gaard

0.16

 branch

0.16

 Branch

0.15

end

0.15

Activations Density 0.058%

references to geographical directions or locations

No Comments

No Known Activations