INDEX

Explanations

phrases indicating instances of connection, association, or implied relationships among various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ocator

-0.15

aja

-0.15

\Client

-0.14

 Redistributions

-0.14

ekk

-0.14

ãĤĥ

-0.14

ãĥĢãĥ¼

-0.13

ìĭł

-0.13

Ð¾Ð²ÑĸÐ´

-0.13

POSITIVE LOGITS

Ã¼zel

0.16

and

0.15

ep

0.15

Cancelled

0.15

chÃ©

0.14

mol

0.14

fl

0.14

eza

0.14

è¼Ŀ

0.14

or

0.14

Activations Density 0.088%

phrases indicating instances of connection, association, or implied relationships among various subjects

No Comments

No Known Activations