INDEX

Explanations

instances of key phrases and patterns indicative of discourse related to opinions or statements about political and social issues

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

Ã¸y

-0.17

-0.15

ãĥŃãĥ¼

-0.15

-LAST

-0.15

orthand

-0.15

ezier

-0.15

ĵ°

-0.15

QN

-0.15

acman

-0.14

ÑĩÐ°ÑĤ

-0.14

POSITIVE LOGITS

 COVID

0.16

 actually

0.15

0.14

↵

0.14

fo

0.14

 indeed

0.14

Flush

0.14

0.13

nt

0.13

Activations Density 0.001%

instances of key phrases and patterns indicative of discourse related to opinions or statements about political and social issues

No Comments

No Known Activations