INDEX

Explanations

adverbs and their forms, particularly those that convey manner or degree

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.17

pu

-0.16

sg

-0.15

sto

-0.15

cu

-0.15

iful

-0.15

uai

-0.14

quil

-0.14

tron

-0.14

POSITIVE LOGITS

referrer

0.16

esch

0.15

tics

0.15

uger

0.15

 Speaking

0.14

ãĤ·ãĤ¢

0.14

Ã©ric

0.14

spe

0.14

 Ø§ÙĦØ§Ø¹

0.14

ktion

0.14

Activations Density 0.456%

adverbs and their forms, particularly those that convey manner or degree

No Comments

No Known Activations