INDEX

Explanations

expressions related to analysis, evaluation, and critical thinking in various contexts

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

alom

-0.17

ifer

-0.15

ainter

-0.15

Ð°Ð»Ð¾Ð¼

-0.15

ëŀ

-0.14

Hin

-0.14

anche

-0.14

itzer

-0.14

ced

-0.14

aed

-0.14

POSITIVE LOGITS

 Others

0.18

 others

0.18

 rather

0.17

Others

0.16

others

0.16

rather

0.15

ãĥ¥

0.15

 without

0.14

 Rather

0.14

without

0.14

Activations Density 0.363%

expressions related to analysis, evaluation, and critical thinking in various contexts

No Comments

No Known Activations