INDEX

Explanations

terms related to killing or slaughtering, particularly in the context of both animals and significant historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.18

 creep

-0.17

Ã¼f

-0.16

cre

-0.16

igo

-0.15

Cre

-0.15

infeld

-0.15

keh

-0.15

 Creed

-0.14

POSITIVE LOGITS

ï»¿#

0.16

Ã¡mara

0.15

erp

0.15

.sha

0.15

Ð¾Ð¶Ðµ

0.14

phin

0.14

 okres

0.14

BoxLayout

0.14

olk

0.14

ENTIC

0.13

Activations Density 0.013%

terms related to killing or slaughtering, particularly in the context of both animals and significant historical events

No Comments

No Known Activations