INDEX

Explanations

specific coding or error messages within technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ponible

-0.15

 zoekt

-0.14

 parc

-0.14

 Ø§ÙĦØ¹Ø¸

-0.14

 Sick

-0.14

duk

-0.14

USR

-0.14

oku

-0.14

imoto

-0.14

erea

-0.13

POSITIVE LOGITS

oop

0.15

nap

0.15

quette

0.14

"#

0.14

 clearing

0.14

abo

0.14

ilon

0.14

COPE

0.14

RELATED

0.14

Nap

0.14

Activations Density 0.000%

specific coding or error messages within technical documentation

No Comments

No Known Activations