INDEX

Explanations

parameters and return 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

heimer

-0.17

ssel

-0.16

igen

-0.15

ega

-0.15

Wor

-0.14

orig

-0.14

atha

-0.14

ertain

-0.14

anya

-0.14

division

-0.14

POSITIVE LOGITS

[in

0.19

param

0.18

 cref

0.18

 param

0.18

[out

0.17

IRST

0.16

hill

0.15

 Param

0.15

ãģ®äºº

0.15

ertools

0.14

Activations Density 0.003%

parameters and return statements in code

No Comments

No Known Activations