INDEX

Explanations

technical commands and error messages related to software or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Lowe

-0.15

ephy

-0.15

Ø·Ø¹

-0.14

ended

-0.14

ÙĬØªÙĬ

-0.13

 aster

-0.13

à¹Ģà¸ģà¸¥

-0.13

ruba

-0.13

 Proof

-0.13

POSITIVE LOGITS

Lua

0.19

 íĭ

0.17

TemplateName

0.16

ãĥ¥

0.16

íĭĢ

0.16

ullo

0.16

/core

0.15

 Commons

0.15

 }}↵

0.15

ordinal

0.15

Activations Density 0.023%

technical commands and error messages related to software or systems

No Comments

No Known Activations