INDEX

Explanations

instances of numerical values or sequences in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wind

-0.18

wend

-0.16

-0.15

tro

-0.15

als

-0.15

stre

-0.15

isti

-0.15

aid

-0.15

hill

-0.15

pread

-0.14

POSITIVE LOGITS

hoa

0.14

addtogroup

0.14

.angular

0.14

mrt

0.14

_tpl

0.14

Aura

0.14

ayet

0.13

BufferData

0.13

Äįer

0.13

quate

0.13

Activations Density 0.003%

instances of numerical values or sequences in the text

No Comments

No Known Activations