INDEX

Explanations

references to explosive devices or bomb-related terminology

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

ebra

-0.20

-0.17

ERN

-0.15

Ĺi

-0.15

 strengths

-0.15

ernel

-0.14

rious

-0.14

ern

-0.14

ÐµÐ»ÐµÑĦ

-0.14

omanip

-0.14

POSITIVE LOGITS

aging

0.17

.await

0.15

UGIN

0.15

alink

0.15

iani

0.14

shell

0.14

ersh

0.14

Ð¸ÑĢÐ¾Ð²

0.14

_funcs

0.14

.dir

0.14

Activations Density 0.010%

references to explosive devices or bomb-related terminology

No Comments

No Known Activations