INDEX

Explanations

informal expressions and dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ochen

-0.15

å¦ĸ

-0.15

thouse

-0.14

iche

-0.14

HEST

-0.14

elder

-0.14

height

-0.14

SPA

-0.14

.AppendFormat

-0.14

ibo

-0.13

POSITIVE LOGITS

arih

0.17

 konkrÃ©t

0.16

akes

0.15

ä¸²

0.15

ulent

0.14

ģm

0.14

cion

0.14

geber

0.14

mad

0.14

Activations Density 0.109%

informal expressions and dialogue

No Comments

No Known Activations