INDEX

Explanations

XML opening tags

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

eldom

-0.17

agate

-0.15

bulan

-0.15

Latch

-0.14

å¡

-0.13

Credential

-0.13

mul

-0.13

oleon

-0.13

ï»¿↵↵

-0.13

¼

-0.13

POSITIVE LOGITS

ugi

0.15

aha

0.14

_OS

0.14

è¯Ń

0.14

 soci

0.13

kker

0.13

 Soci

0.13

_fitness

0.13

OS

0.13

Activations Density 0.078%

XML opening tags

No Comments

No Known Activations