INDEX

Explanations

instances of the word "detailed" and related phrases indicating in-depth descriptions or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

åĪĢ

-0.18

Å¡t

-0.16

kola

-0.15

dera

-0.15

malink

-0.14

alloc

-0.14

esel

-0.14

ATAB

-0.14

IRC

-0.13

oya

-0.13

POSITIVE LOGITS

íŀĪ

0.16

ago

0.15

mente

0.15

ãĥ¼ãĥĢ

0.14

_macro

0.14

 Mack

0.13

.compat

0.13

rophe

0.13

/lg

0.13

Ø±Ø§ÙĨÛĮ

0.13

Activations Density 0.017%

instances of the word "detailed" and related phrases indicating in-depth descriptions or analyses

No Comments

No Known Activations