INDEX

Explanations

conjunctions that indicate connectivity or emphasis in relationships between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

avored

-0.17

ustos

-0.16

itzer

-0.15

erais

-0.15

benhavn

-0.14

erli

-0.14

sko

-0.14

ÎºÎ®

-0.14

Ð°ÑĤÐºÐ¾Ð²

-0.14

(çģ«

-0.14

POSITIVE LOGITS

APON

0.15

 GÃ¼

0.15

-or

0.14

apon

0.14

 Antar

0.14

Gul

0.14

0.13

rog

0.13

wn

0.13

Activations Density 0.031%

conjunctions that indicate connectivity or emphasis in relationships between ideas

No Comments

No Known Activations