INDEX

Explanations

textual elements and numeric details, such as quotes, references, measurements, and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

znam

-0.13

atu

-0.13

Ø³ØªØ§ÙĨ

-0.12

eless

-0.12

AMA

-0.12

ibs

-0.12

ARAM

-0.12

plode

-0.12

OTO

-0.12

POSITIVE LOGITS

0.31

0.14

ï¼Ĵï¼Ĳ

0.14

Ù¡

0.13

ingle

0.12

á»©a

0.12

Ð°Ð½Ð¸ÑĨ

0.12

ign

0.12

ÛĮÙĨÙĩ

0.12

Activations Density 0.992%

textual elements and numeric details, such as quotes, references, measurements, and formatting

No Comments

No Known Activations