INDEX

Explanations

references to specific times or dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

number

-0.16

RIX

-0.15

avra

-0.15

ALLED

-0.14

Number

-0.14

ched

-0.14

Ð½Ð°ÑĢ

-0.14

licer

-0.14

imuth

-0.14

 number

-0.14

POSITIVE LOGITS

 anytime

0.25

 later

0.23

no

0.21

 earliest

0.20

-w

0.19

 mutually

0.18

 scheduled

0.18

 greatly

0.17

 little

0.17

 dates

0.17

Activations Density 0.067%

references to specific times or dates

No Comments

No Known Activations