INDEX

Explanations

numeric values and quantities in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

_framework

-0.14

uct

-0.14

ï»¿#

-0.14

çķ°

-0.14

 Magn

-0.14

bew

-0.14

ENABLE

-0.14

byt

-0.14

_subscribe

-0.13

POSITIVE LOGITS

edList

0.16

ateria

0.15

iro

0.15

agens

0.14

iens

0.14

ä»¥ä¸Ĭ

0.14

onte

0.14

ëļ

0.13

atsby

0.13

iken

0.13

Activations Density 0.176%

numeric values and quantities in descriptions

No Comments

No Known Activations