INDEX

Explanations

references to file structures or project configurations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

_TP

-0.16

ettes

-0.15

alker

-0.15

 AÅŁ

-0.14

engo

-0.14

ynn

-0.14

ASSES

-0.14

ogl

-0.14

POSITIVE LOGITS

uger

0.16

ãĥ³ãĥĲãĥ¼

0.14

them

0.14

StringRef

0.14

Ø¨Ø·

0.13

Î¼Î¹

0.13

jom

0.13

ugar

0.13

_trap

0.13

velte

0.13

Activations Density 0.043%

references to file structures or project configurations in programming contexts

No Comments

No Known Activations