INDEX

Explanations

patterns related to dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ramework

-0.18

chwitz

-0.17

DCALL

-0.16

rieb

-0.15

ibly

-0.15

jer

-0.15

ouver

-0.15

Ð¾Ð»ÐµÑĤ

-0.14

umeric

-0.14

veau

-0.14

POSITIVE LOGITS

 Townsend

0.16

len

0.15

ent

0.15

 Penny

0.14

ling

0.14

PIO

0.14

AndWait

0.14

fen

0.13

 disp

0.13

pr

0.13

Activations Density 0.008%

patterns related to dates and numerical data

No Comments

No Known Activations