INDEX

Explanations

references to the name "Bro" in various contexts

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

 Harden

-0.15

erva

-0.15

 conven

-0.15

false

-0.15

uary

-0.14

istas

-0.14

/history

-0.13

keeper

-0.13

Ley

-0.13

POSITIVE LOGITS

FIT

0.16

.updateDynamic

0.15

elf

0.14

iginal

0.14

å§ĵ

0.14

Comparable

0.14

(EFFECT

0.14

Stencil

0.13

ucene

0.13

doe

0.13

Activations Density 0.006%

references to the name "Bro" in various contexts

No Comments

No Known Activations