INDEX

Explanations

expressions of belief or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

upo

-0.17

ilib

-0.15

apiro

-0.15

abwe

-0.15

ainers

-0.14

bah

-0.14

uitka

-0.14

assium

-0.14

setLabel

-0.14

aÅ¾

-0.14

POSITIVE LOGITS

eo

0.17

_brand

0.14

AndView

0.14

Ø§ÙĦÛĮ

0.14

 Shen

0.14

subst

0.13

/IP

0.13

 core

0.13

 Gunn

0.13

/Table

0.13

Activations Density 0.058%

expressions of belief or opinion

No Comments

No Known Activations