INDEX

Explanations

terms related to death and loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 porr

-0.18

quiv

-0.16

anki

-0.15

esk

-0.15

iddet

-0.15

%%%%

-0.15

ng

-0.15

jmu

-0.15

APS

-0.14

aqu

-0.14

POSITIVE LOGITS

eca

0.16

ëĮĢ

0.16

-cache

0.15

 Cong

0.15

 replaced

0.14

 Telescope

0.14

opt

0.14

ãĤĢ

0.14

 crime

0.14

Activations Density 0.241%

terms related to death and loss

No Comments

No Known Activations