INDEX

Explanations

numerical data and statistics typically related to studies or research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

allet

-0.18

itmap

-0.15

eters

-0.15

rick

-0.14

ror

-0.14

_JUMP

-0.14

ucks

-0.14

 Kapoor

-0.13

rey

-0.13

 ticking

-0.13

POSITIVE LOGITS

0.26

0.25

0.23

0.22

Activations Density 0.066%

numerical data and statistics typically related to studies or research findings

No Comments

No Known Activations