INDEX

Explanations

references to measurements, quantities, and lists of elements or components

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

essian

-0.19

iga

-0.16

owers

-0.14

engine

-0.14

ertz

-0.14

dex

-0.14

lon

-0.13

dot

-0.13

POSITIVE LOGITS

sten

0.18

Mappings

0.15

ListNode

0.15

/vendors

0.14

izophren

0.14

cai

0.14

_pes

0.14

.appendTo

0.14

_TRACE

0.14

metis

0.14

Activations Density 0.058%

references to measurements, quantities, and lists of elements or components

No Comments

No Known Activations