INDEX

Explanations

negative evaluations and terminology related to film reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

è¥

-0.16

 second

-0.15

 fond

-0.15

second

-0.14

ylim

-0.14

 segundo

-0.14

 Sinai

-0.14

.second

-0.13

 append

-0.13

è·

-0.13

POSITIVE LOGITS

 third

0.21

 Third

0.21

Third

0.21

 THIRD

0.19

third

0.18

_third

0.18

 thirds

0.17

Ð°ÑģÑģ

0.16

-third

0.15

_allocated

0.15

Activations Density 0.243%

negative evaluations and terminology related to film reviews

No Comments

No Known Activations

negative evaluations and terminology related to film reviews

No Comments

No Known Activations