INDEX

Explanations

code snippets and structure related to programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iry

-0.16

endoza

-0.15

èĶµ

-0.15

Indented

-0.15

quete

-0.15

stk

-0.15

ongs

-0.15

chia

-0.14

icho

-0.14

POSITIVE LOGITS

 Vall

0.15

.UTF

0.15

cona

0.15

ynam

0.14

emente

0.14

enced

0.14

_BITS

0.14

exc

0.14

aste

0.14

 apart

0.13

Activations Density 0.114%

code snippets and structure related to programming

No Comments

No Known Activations