INDEX

Explanations

code-related constructs and programming patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ise

-0.18

ozem

-0.18

olson

-0.17

cak

-0.16

 Agenda

-0.15

lug

-0.15

Fra

-0.15

arial

-0.14

arse

-0.14

ambi

-0.14

POSITIVE LOGITS

ople

0.17

illis

0.17

ToProps

0.15

bis

0.15

ghi

0.15

ocked

0.14

bis

0.14

lesen

0.14

bens

0.14

ãĥ¼ãĥĪ

0.14

Activations Density 0.070%

code-related constructs and programming patterns

No Comments

No Known Activations