INDEX

Explanations

references to population studies and related academic outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ingu

-0.16

iegel

-0.15

weeney

-0.15

oot

-0.15

ivec

-0.14

ertz

-0.13

Ð²ÐµÑĢÐ´

-0.13

ARTH

-0.13

 Gilles

-0.13

ATAB

-0.13

POSITIVE LOGITS

ateway

0.16

.opend

0.16

 whose

0.14

.EventQueue

0.14

acies

0.14

hsi

0.13

avier

0.13

âĸº

0.13

Ã¤

0.13

avin

0.13

Activations Density 0.009%

references to population studies and related academic outputs

No Comments

No Known Activations