INDEX

Explanations

actions related to bending or lowering one's body

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urum

-0.17

riel

-0.16

SAT

-0.16

etat

-0.15

vala

-0.14

Ð¾Ð±ÑĢÐµÑĤ

-0.14

icari

-0.14

vla

-0.14

 systemd

-0.14

uchi

-0.14

POSITIVE LOGITS

 bending

0.16

éĻį

0.15

ault

0.15

 bend

0.15

alty

0.15

Authenticate

0.15

 bent

0.14

Bow

0.14

 Garrett

0.14

cis

0.14

Activations Density 0.072%

actions related to bending or lowering one's body

No Comments

No Known Activations