INDEX

Explanations

terms related to protests and demonstrations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Helmet

-0.17

-0.14

pedia

-0.14

 Pros

-0.14

 Larson

-0.14

FUL

-0.14

.Design

-0.13

anou

-0.13

 ï¿¥

-0.13

Rum

-0.13

POSITIVE LOGITS

aby

0.17

.vol

0.15

arat

0.15

cond

0.15

ityEngine

0.14

abis

0.14

é¢Ĩ

0.14

Ð¾Ñī

0.14

umont

0.14

_dispatcher

0.14

Activations Density 0.182%

terms related to protests and demonstrations

No Comments

No Known Activations