INDEX

Explanations

terms related to endings or conclusions, particularly focusing on life events and their abrupt cessation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 away

-0.18

 Away

-0.18

aways

-0.15

.plus

-0.15

away

-0.14

Away

-0.14

¹

-0.14

moid

-0.14

plet

-0.14

ìķĦ

-0.14

POSITIVE LOGITS

reich

0.16

anc

0.16

ocos

0.16

(stop

0.16

orses

0.16

indre

0.15

ols

0.15

.asp

0.15

axon

0.14

Activations Density 0.175%

terms related to endings or conclusions, particularly focusing on life events and their abrupt cessation

No Comments

No Known Activations