INDEX

Explanations

adjectives and adverbial forms ending in "ly" or "ary."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

resa

-0.16

iera

-0.16

istar

-0.15

awai

-0.14

ifo

-0.14

ãĤ©

-0.14

canf

-0.14

sey

-0.14

ires

-0.14

itu

-0.13

POSITIVE LOGITS

nx

0.23

nda

0.22

eo

0.21

nn

0.21

lation

0.21

ng

0.20

ssel

0.20

nnen

0.20

nder

0.19

lated

0.19

Activations Density 0.058%

adjectives and adverbial forms ending in "ly" or "ary."

No Comments

No Known Activations

adjectives and adverbial forms ending in "ly" or "ary."

No Comments

No Known Activations