INDEX

Explanations

programming-related keywords and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/Dk

-0.15

-selector

-0.15

interop

-0.15

 RuntimeObject

-0.15

mlink

-0.15

ÏħÎ¼

-0.14

legen

-0.14

áº¤

-0.14

uci

-0.14

/***/

-0.14

POSITIVE LOGITS

 Gord

0.16

 Romero

0.16

<-

0.15

hy

0.15

 Petty

0.14

ja

0.14

edor

0.14

strconv

0.14

 strconv

0.14

Activations Density 0.028%

programming-related keywords and structures

No Comments

No Known Activations