INDEX

Explanations

words and phrases related to honoring or commemorating individuals or groups

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

ÐµÐ½Ñģ

-0.16

ÐµÑĢÐº

-0.15

.Core

-0.15

flix

-0.15

plet

-0.15

\Core

-0.15

lander

-0.15

indle

-0.15

plode

-0.15

wis

-0.15

POSITIVE LOGITS

uÅŁ

0.15

dq

0.15

 bidi

0.14

 typedef

0.14

itz

0.14

odor

0.13

gaard

0.13

mounted

0.13

éĴŁ

0.13

 Ð²ÐµÑĩ

0.13

Activations Density 0.019%

words and phrases related to honoring or commemorating individuals or groups

No Comments

No Known Activations