INDEX

Explanations

phrases indicating degrees of measurement or evaluation, particularly in relation to scores or ratings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aman

-0.17

 Seed

-0.15

uin

-0.15

æĻ´

-0.14

iment

-0.14

 Mann

-0.14

ibar

-0.14

Seed

-0.13

eneral

-0.13

ulf

-0.13

POSITIVE LOGITS

 sinc

0.17

acco

0.16

ollah

0.14

FONT

0.14

.thumb

0.14

orden

0.14

resco

0.13

ãĥ³ãĤº

0.13

.DefaultCellStyle

0.13

acos

0.13

Activations Density 0.028%

phrases indicating degrees of measurement or evaluation, particularly in relation to scores or ratings

No Comments

No Known Activations