INDEX

Explanations

references to real-time data or monitoring

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

enticator

-0.16

erer

-0.15

bum

-0.15

sage

-0.15

mdb

-0.15

olib

-0.15

unga

-0.15

lhs

-0.15

roup

-0.14

arel

-0.14

POSITIVE LOGITS

vis

0.16

akit

0.16

okit

0.16

orio

0.15

active

0.14

andro

0.14

AVIS

0.14

.SetToolTip

0.14

enegro

0.14

Cho

0.14

Activations Density 0.014%

references to real-time data or monitoring

No Comments

No Known Activations