INDEX

Explanations

actions related to announcements and unveilings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.scalablytyped

-0.17

ActionCreators

-0.15

:async

-0.14

cratch

-0.14

velt

-0.14

yonel

-0.13

ÑĨÐµÐ¿

-0.13

zin

-0.13

ï»¿#

-0.13

elper

-0.13

POSITIVE LOGITS

/-

0.15

uce

0.15

que

0.15

pst

0.15

ongan

0.14

pez

0.14

dit

0.14

ILLISECONDS

0.14

Dit

0.14

Activations Density 0.000%

actions related to announcements and unveilings

No Comments

No Known Activations