INDEX

Explanations

terms related to professional experiences and career progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

atica

-0.16

iw

-0.14

BoundingBox

-0.13

utos

-0.13

skb

-0.13

ëĿ¼ë§Ī

-0.13

amines

-0.13

STEM

-0.13

Ãªn

-0.13

æº

-0.13

POSITIVE LOGITS

 spells

0.52

 spell

0.49

st

0.47

 stint

0.41

 Spells

0.41

 SPELL

0.38

 Spell

0.38

spell

0.38

 periods

0.36

 brief

0.35

Activations Density 0.145%

terms related to professional experiences and career progression

No Comments

No Known Activations