INDEX

Explanations

instances of the word "big."

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

prus

-0.15

urence

-0.15

ez

-0.15

IDDEN

-0.14

_NOP

-0.14

htag

-0.14

 backpage

-0.14

ral

-0.14

usz

-0.14

ettings

-0.14

POSITIVE LOGITS

oted

0.22

otre

0.16

ots

0.16

elow

0.16

ging

0.15

 Ã¶lÃ§Ã¼de

0.15

anned

0.15

-ticket

0.15

win

0.14

wei

0.14

Activations Density 0.032%

instances of the word "big."

No Comments

No Known Activations