INDEX

Explanations

explanations and relationships related to scientific theories and their support

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

verbatim

-0.16

nga

-0.15

voj

-0.14

illa

-0.13

ild

-0.13

á»Ļc

-0.13

eling

-0.13

_PI

-0.13

neas

-0.12

.Sdk

-0.12

POSITIVE LOGITS

 explanation

1.12

 explain

1.10

 explanations

1.05

 explaining

1.03

 explains

1.00

 explained

0.98

 Explanation

0.96

 Explain

0.90

Explanation

0.90

explain

0.90

Activations Density 0.292%

explanations and relationships related to scientific theories and their support

No Comments

No Known Activations