INDEX

Explanations

formatted or structured data, including visual separators and underscores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Callable

-0.15

alla

-0.15

eller

-0.14

prise

-0.14

elong

-0.14

lotte

-0.14

Ã½Å¡

-0.14

outil

-0.14

ervals

-0.14

Äĥ

-0.13

POSITIVE LOGITS

0.17

áºŃu

0.17

Kun

0.15

±

0.14

BUG

0.14

paged

0.14

0.13

ibly

0.13

 scrap

0.13

Activations Density 0.005%

formatted or structured data, including visual separators and underscores

No Comments

No Known Activations