INDEX

Explanations

adjectives and adverbial forms related to effects or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.19

edList

-0.19

on

-0.15

Ð¸ÑĤÐ¾Ð¼

-0.15

ri

-0.15

udio

-0.14

onis

-0.14

ular

-0.14

Sor

-0.14

rof

-0.14

POSITIVE LOGITS

 acid

0.20

olumn

0.16

WER

0.15

ziaÅĤ

0.15

acid

0.15

 ÑĢÐ°Ð±

0.14

/apis

0.14

 Acid

0.14

ardown

0.14

¿

0.14

Activations Density 0.081%

adjectives and adverbial forms related to effects or characteristics

No Comments

No Known Activations

adjectives and adverbial forms related to effects or characteristics

No Comments

No Known Activations