INDEX

Explanations

references to reports or statements made by organizations or research firms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ruba

-0.17

oplevel

-0.16

ilk

-0.15

-runtime

-0.15

uel

-0.15

ÐµÐºÑģÐ¸

-0.14

è¨º

-0.14

 Seznam

-0.14

clusive

-0.13

{@

-0.13

POSITIVE LOGITS

 stump

0.16

eree

0.16

æ·

0.15

itti

0.15

Ø¹Ø¨

0.14

nds

0.14

anton

0.14

levator

0.14

avian

0.13

ders

0.13

Activations Density 0.028%

references to reports or statements made by organizations or research firms

No Comments

No Known Activations