INDEX

Explanations

programming-related keywords and error handling terms

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

 Closure

-0.15

Closure

-0.15

ervlet

-0.15

 closures

-0.14

ÑĤÐ¸Ñı

-0.14

[NUM

-0.13

icl

-0.13

uche

-0.13

aux

-0.13

 Organization

-0.13

POSITIVE LOGITS

ometr

0.15

po

0.13

ModelState

0.13

modelName

0.13

unf

0.13

Urb

0.13

.githubusercontent

0.13

zyst

0.12

addtogroup

0.12

BW

0.12

Activations Density 0.052%

programming-related keywords and error handling terms

No Comments

No Known Activations