INDEX

Explanations

variable assignments and function calls in code snippets

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

rawn

-0.16

à¸´à¸§

-0.16

uron

-0.16

ullan

-0.15

FullYear

-0.14

 Shepherd

-0.14

 Shepard

-0.14

 Wheel

-0.14

uro

-0.14

inski

-0.14

POSITIVE LOGITS

eldon

0.19

nett

0.17

aidu

0.15

SF

0.14

Eld

0.14

 novel

0.14

irth

0.14

abil

0.14

]("

0.13

ÎºÏģÎ¹

0.13

Activations Density 0.085%

variable assignments and function calls in code snippets

No Comments

No Known Activations