INDEX

Explanations

unique characters or symbols indicating special significance or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 enumerator

-0.15

_CTX

-0.15

 enumeration

-0.14

 Enumeration

-0.14

 enzym

-0.14

.dtype

-0.14

 enzyme

-0.14

Enumer

-0.14

 envelop

-0.14

Ã¤nger

-0.14

POSITIVE LOGITS

kind

0.25

 kind

0.25

moon

0.24

 moon

0.24

Kind

0.22

Moon

0.21

 Moon

0.21

 kinds

0.21

-kind

0.21

 Kind

0.21

Activations Density 0.002%

unique characters or symbols indicating special significance or formatting

No Comments

No Known Activations