INDEX

Explanations

conditional expressions and phrases indicating personal preferences or choices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ìī

-0.15

ãĤ¦ãĤ¹

-0.15

nine

-0.14

tam

-0.14

_GU

-0.13

AGIC

-0.13

rial

-0.13

aeda

-0.13

'post

-0.13

pio

-0.13

POSITIVE LOGITS

 Serialized

0.16

wend

0.15

irms

0.15

asher

0.14

moz

0.14

bose

0.14

arda

0.14

maries

0.13

oce

0.13

LAG

0.13

Activations Density 0.101%

conditional expressions and phrases indicating personal preferences or choices

No Comments

No Known Activations