INDEX

Explanations

words that indicate structural definitions or refer to specific entities, often with legal or cultural implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

EG

-0.16

ibbon

-0.15

 Becker

-0.14

jn

-0.14

 fixed

-0.14

lÃ¡n

-0.14

isko

-0.14

 Bilim

-0.14

%#

-0.14

ifica

-0.13

POSITIVE LOGITS

/fa

0.15

annels

0.15

rell

0.14

IDGET

0.14

iais

0.14

oca

0.14

 è©

0.14

osto

0.14

Activations Density 0.055%

words that indicate structural definitions or refer to specific entities, often with legal or cultural implications

No Comments

No Known Activations