INDEX

Explanations

critiques and shortcomings related to film narratives and production elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Suff

-0.15

ansi

-0.15

 hood

-0.14

rary

-0.14

arker

-0.13

ayette

-0.13

atin

-0.13

siyon

-0.13

bli

-0.13

sj

-0.13

POSITIVE LOGITS

integral

0.20

 detr

0.20

 impact

0.18

Jar

0.18

Jar

0.18

jar

0.17

 integral

0.17

 Natural

0.17

Auth

0.17

jar

0.17

Activations Density 0.201%

critiques and shortcomings related to film narratives and production elements

No Comments

No Known Activations