INDEX

Explanations

instances of the word "mention" and its variations in context

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

oen

-0.15

idal

-0.14

dez

-0.14

nze

-0.14

ylum

-0.14

topl

-0.13

raith

-0.13

anas

-0.13

Unhandled

-0.13

kup

-0.13

POSITIVE LOGITS

erdale

0.19

isan

0.15

ullet

0.15

Ä±rak

0.15

isky

0.14

ipo

0.14

 Soph

0.14

ecta

0.14

åĲĽ

0.14

erva

0.14

Activations Density 0.006%

instances of the word "mention" and its variations in context

No Comments

No Known Activations