INDEX

Explanations

mentions of specific names and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

elerik

-0.17

portlet

-0.15

UNUSED

-0.15

avior

-0.15

á»Ļn

-0.15

anlar

-0.14

IIIK

-0.14

ONA

-0.14

ÂłPS

-0.13

ellig

-0.13

POSITIVE LOGITS

0.16

eto

0.15

asar

0.15

 Ether

0.15

 spells

0.15

ao

0.15

omi

0.14

on

0.14

Activations Density 0.198%

mentions of specific names and entities

No Comments

No Known Activations