INDEX

Explanations

phrases and references related to knowledge and understanding of various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

»

-0.17

antine

-0.15

olia

-0.15

aldi

-0.14

LATED

-0.14

ross

-0.14

alon

-0.14

_clock

-0.14

gaard

-0.13

uent

-0.13

POSITIVE LOGITS

isl

0.19

å¦Ĥä½ķ

0.17

how

0.16

ìļ

0.15

 Ð¿ÑĥÑĤ

0.14

how

0.14

emax

0.14

ourcem

0.14

hlen

0.14

addy

0.14

Activations Density 0.076%

phrases and references related to knowledge and understanding of various subjects

No Comments

No Known Activations