INDEX

Explanations

occurrences of import statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ambi

-0.18

atch

-0.17

çĨ

-0.16

ven

-0.15

olia

-0.15

moth

-0.14

mina

-0.14

lok

-0.14

dera

-0.14

SB

-0.14

POSITIVE LOGITS

ANGE

0.14

ATIO

0.14

íĸ¥

0.13

 unst

0.13

ÑĬ

0.13

avier

0.13

Rek

0.13

arf

0.13

GLE

0.13

.Generated

0.13

Activations Density 0.002%

occurrences of import statements in code

No Comments

No Known Activations