INDEX

Explanations

connections and relations in text, particularly those that link different ideas or actions

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

ãĥ³ãĤ¬

-0.18

alus

-0.17

alo

-0.16

gba

-0.15

 Kiss

-0.15

estre

-0.15

ëĭ¥

-0.15

 alike

-0.15

çĲ³

-0.14

igli

-0.14

POSITIVE LOGITS

Laz

0.15

itung

0.14

igon

0.14

 Arth

0.14

ocol

0.13

zcze

0.13

PropertyDescriptor

0.13

ovenant

0.13

ingleton

0.13

Gon

0.13

Activations Density 0.099%

connections and relations in text, particularly those that link different ideas or actions

No Comments

No Known Activations