INDEX

Explanations

keywords and structure related to programming functions and their visibility modifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

asl

-0.15

ectl

-0.14

ãĥĥãĤ¯ãĤ¹

-0.14

owego

-0.14

onta

-0.14

oke

-0.13

arning

-0.13

GES

-0.13

xes

-0.13

_EMIT

-0.13

POSITIVE LOGITS

èķ

0.14

 Pert

0.14

 UNUSED

0.14

CA

0.14

ca

0.14

ie

0.13

 Coupe

0.13

dea

0.13

bye

0.13

quier

0.13

Activations Density 0.063%

keywords and structure related to programming functions and their visibility modifiers

No Comments

No Known Activations