INDEX

Explanations

mentions of television networks and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_closure

-0.15

Ã«n

-0.15

tings

-0.15

posables

-0.15

ÐµÐ»ÑĮÐ·Ñı

-0.15

 mortal

-0.14

mor

-0.14

 radios

-0.14

hab

-0.14

 Radio

-0.14

POSITIVE LOGITS

 Segment

0.19

ç¯Ģ

0.18

çķªçµĦ

0.17

programs

0.17

.Program

0.17

èĬĤ

0.17

 Program

0.16

 programming

0.16

 program

0.16

 episodes

0.16

Activations Density 0.048%

mentions of television networks and programs

No Comments

No Known Activations