INDEX

Explanations

segments of code related to functions, events, and their associated properties or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ADDE

-0.16

Ä±y

-0.15

istrovstvÃŃ

-0.15

issen

-0.15

cav

-0.15

viso

-0.14

xED

-0.14

 cave

-0.14

ÌĨ

-0.14

DOT

-0.14

POSITIVE LOGITS

 Eval

0.14

ason

0.14

 Found

0.14

/op

0.13

UGH

0.13

meter

0.13

 Ð¾ÑĢÐ³

0.13

ych

0.13

yal

0.13

Activations Density 0.542%

segments of code related to functions, events, and their associated properties or attributes

No Comments

No Known Activations