INDEX

Explanations

terminology related to various 'isms' and ideologies, particularly focusing on political and social movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

pad

-0.17

able

-0.16

gether

-0.15

cott

-0.15

aghan

-0.15

oom

-0.14

let

-0.14

ing

-0.14

own

-0.14

who

-0.14

POSITIVE LOGITS

adil

0.16

perature

0.15

ality

0.15

anness

0.15

pora

0.15

atically

0.15

CF

0.14

é¡Ķ

0.14

èĢħçļĦ

0.14

ometrics

0.14

Activations Density 0.103%

terminology related to various 'isms' and ideologies, particularly focusing on political and social movements

No Comments

No Known Activations