INDEX

Explanations

references to sections and figures within a document

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

ì§ĳ

-0.15

 zwar

-0.15

_UNIX

-0.15

atorial

-0.14

.Experimental

-0.14

èĤ¯

-0.14

åŃĺäºİ

-0.13

oru

-0.13

ÐµÐ´

-0.13

ÐµÑĤÑĥ

-0.13

POSITIVE LOGITS

ÏĥÎ·

0.14

eea

0.14

makt

0.14

icari

0.14

0.13

indi

0.13

morgan

0.13

ï¸

0.13

ayla

0.13

opsis

0.13

Activations Density 0.042%

references to sections and figures within a document

No Comments

No Known Activations