INDEX

Explanations

numerical data, specifically dates and numerical details related to significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

amb

-0.17

ÙĦØ§Øª

-0.16

imp

-0.16

 forth

-0.15

amen

-0.14

ample

-0.14

 altern

-0.14

ature

-0.14

tem

-0.14

unate

-0.14

POSITIVE LOGITS

phinx

0.18

ritz

0.17

ysz

0.17

stell

0.16

trys

0.16

abis

0.16

CRYPT

0.15

caff

0.15

quist

0.15

weis

0.15

Activations Density 0.038%

numerical data, specifically dates and numerical details related to significant events

No Comments

No Known Activations