INDEX

Explanations

keywords and phrases indicating specific topics or themes relevant to academic or scientific discussions

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

 GenerationType

-0.16

Tp

-0.15

æ··åĲĪ

-0.15

º«

-0.15

.norm

-0.14

_codegen

-0.14

irim

-0.14

DEX

-0.14

 Grat

-0.14

iode

-0.14

POSITIVE LOGITS

ar

0.18

0.15

 conc

0.15

.Support

0.15

ulta

0.15

 current

0.14

 genu

0.14

 expectation

0.14

 case

0.14

Activations Density 0.004%

keywords and phrases indicating specific topics or themes relevant to academic or scientific discussions

No Comments

No Known Activations