INDEX

Explanations

mentions of causes related to various contexts, often in a problem-solution or event-description format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ontrol

-0.17

ersistence

-0.16

nah

-0.15

ewis

-0.15

 Newsp

-0.14

-dot

-0.14

coni

-0.14

Å©i

-0.14

 Transportation

-0.14

hare

-0.14

POSITIVE LOGITS

 hack

0.16

URN

0.15

ÑĤÐµÑĢÐ½

0.14

gres

0.14

ijk

0.13

roj

0.13

 hospital

0.13

ivÃ©

0.13

ido

0.13

uran

0.13

Activations Density 0.017%

mentions of causes related to various contexts, often in a problem-solution or event-description format

No Comments

No Known Activations