INDEX

Explanations

references to holograms and holographic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ø¶Ø§

-0.16

sert

-0.15

STRU

-0.15

MaxY

-0.15

ongyang

-0.14

lang

-0.14

ieder

-0.14

Ø¯ÙĬ

-0.14

GGLE

-0.14

ypad

-0.14

POSITIVE LOGITS

Ã¡k

0.15

0.14

facet

0.14

akens

0.14

azing

0.14

oti

0.14

ahn

0.13

Joh

0.13

EE

0.13

indsight

0.13

Activations Density 0.007%

references to holograms and holographic concepts

No Comments

No Known Activations