INDEX

Explanations

terms related to emergency situations or crises

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

izi

-0.19

smith

-0.17

verter

-0.15

efe

-0.15

arra

-0.14

irt

-0.14

switch

-0.13

bec

-0.13

oning

-0.13

 çĽ

-0.13

POSITIVE LOGITS

dir

0.14

ãĥ¼ãĥģ

0.14

 Archive

0.14

 Multip

0.14

oldem

0.14

ÙĪØ§Ø²

0.14

ffen

0.13

 consc

0.13

Activations Density 0.012%

terms related to emergency situations or crises

No Comments

No Known Activations