INDEX

Explanations

references to experts and authorities discussing topics related to analysis and predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ahead

-0.15

YL

-0.14

lue

-0.14

æłª

-0.14

ech

-0.14

Ã¦re

-0.14

statt

-0.13

fte

-0.13

qe

-0.13

Å¥

-0.13

POSITIVE LOGITS

say

0.21

 consensus

0.20

 agree

0.20

 unanim

0.19

 agreement

0.19

 agrees

0.18

say

0.18

 alike

0.17

 agreed

0.17

 unanimous

0.17

Activations Density 0.104%

references to experts and authorities discussing topics related to analysis and predictions

No Comments

No Known Activations