INDEX

Explanations

terms related to emotions and feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

unner

-0.19

esser

-0.17

akeup

-0.17

ë©ĺ

-0.16

 voks

-0.15

wit

-0.15

_MODULES

-0.15

ucken

-0.15

 Ulus

-0.15

aucoup

-0.14

POSITIVE LOGITS

0.16

ran

0.15

trap

0.15

ym

0.14

er

0.14

 baseline

0.14

PCP

0.14

st

0.14

aland

0.14

Activations Density 0.070%

terms related to emotions and feelings

No Comments

No Known Activations