INDEX

Explanations

numerical values and code snippets related to data analysis in R

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ovie

-0.16

lub

-0.15

appy

-0.14

yah

-0.14

oka

-0.14

ace

-0.13

zw

-0.13

ACHI

-0.13

rahim

-0.13

achi

-0.13

POSITIVE LOGITS

imoto

0.14

enne

0.14

rol

0.14

 GetById

0.13

¶ļ

0.13

 conv

0.13

LING

0.13

 Robbins

0.13

 neighbours

0.13

Controls

0.13

Activations Density 0.026%

numerical values and code snippets related to data analysis in R

No Comments

No Known Activations