INDEX

Explanations

phrases indicating shifts in geopolitical focus and relationships

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

itag

-0.15

UTE

-0.15

 vest

-0.14

&S

-0.14

elib

-0.14

apiro

-0.14

 Vest

-0.14

akov

-0.14

 thread

-0.14

 Ethics

-0.14

POSITIVE LOGITS

vo

0.17

agma

0.15

UTDOWN

0.15

inders

0.14

è¼

0.14

ÑĢÐ°Ð²Ð°

0.14

kontakte

0.14

asename

0.14

_nsec

0.14

ignet

0.13

Activations Density 0.165%

phrases indicating shifts in geopolitical focus and relationships

No Known Activations