INDEX

Explanations

references to authors and their contributions in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ibling

-0.16

ired

-0.15

 cover

-0.14

blick

-0.14

.transfer

-0.14

Å¾e

-0.14

 ModelState

-0.14

Î¬Î½ÏĦÎ±

-0.13

LING

-0.13

WR

-0.13

POSITIVE LOGITS

atica

0.16

ijken

0.16

.RightToLeft

0.15

arella

0.15

Rey

0.14

andle

0.14

 Leigh

0.14

 Faul

0.14

affer

0.14

ewith

0.14

Activations Density 0.004%

references to authors and their contributions in academic contexts

No Comments

No Known Activations