INDEX

Explanations

references to arbitrary or nonsensical phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

addtogroup

-0.17

iversit

-0.16

olas

-0.15

UPI

-0.14

affles

-0.14

Bottom

-0.14

 Atomic

-0.14

ADR

-0.14

glas

-0.14

rophe

-0.14

POSITIVE LOGITS

 Welch

0.15

 Contributor

0.15

 typical

0.14

 Thur

0.14

iley

0.14

 Newman

0.14

tring

0.14

typ

0.14

aylor

0.13

Activations Density 0.567%

references to arbitrary or nonsensical phrases

No Comments

No Known Activations