INDEX

Explanations

instances of lists or enumerations within 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 meant

-0.17

oul

-0.15

 spirit

-0.15

Subset

-0.15

util

-0.14

iterals

-0.14

 dust

-0.14

agon

-0.14

 mean

-0.14

 Flexible

-0.14

POSITIVE LOGITS

=list

0.16

ernen

0.16

plist

0.16

arend

0.15

ucene

0.15

icator

0.15

-unstyled

0.15

rvÃ©

0.14

 Liste

0.14

/List

0.14

Activations Density 0.043%

instances of lists or enumerations within the text

No Comments

No Known Activations