INDEX

Explanations

variations and inflections of the adjective "many."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

leton

-0.17

lest

-0.17

oph

-0.16

lett

-0.16

oved

-0.16

.scalablytyped

-0.15

pell

-0.15

ietf

-0.15

 Bras

-0.15

POSITIVE LOGITS

ng

0.17

esterday

0.17

ed

0.16

inkel

0.16

ields

0.16

Ð¾ÑĢÑĤ

0.16

ãĥ¼ãĥ«

0.15

erk

0.15

elm

0.15

edu

0.14

Activations Density 0.095%

variations and inflections of the adjective "many."

No Comments

No Known Activations