INDEX

Explanations

adjectives describing quality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 ilma

-0.14

flen

-0.14

buz

-0.14

IEL

-0.14

lesi

-0.14

ä¼Ŀ

-0.14

.Transactional

-0.13

pid

-0.13

QualifiedName

-0.13

Pid

-0.13

POSITIVE LOGITS

 enough

0.17

arious

0.15

ikt

0.15

ÙĪØ§Ø±

0.14

 Carlton

0.14

ingle

0.14

 theirs

0.13

 indeed

0.13

Ð¾Ð²Ð°ÑĢ

0.13

argar

0.13

Activations Density 0.234%

adjectives describing quality or condition

No Comments

No Known Activations