INDEX

Explanations

occurrences of the preposition "in" and related contextual phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

tered

-0.15

stdcall

-0.14

acher

-0.14

 Mastery

-0.14

raith

-0.14

ooter

-0.14

oS

-0.14

elight

-0.14

.scalablytyped

-0.14

.ga

-0.14

POSITIVE LOGITS

omen

0.15

acco

0.15

áº¿p

0.15

ounce

0.14

ĥĿ

0.14

 oceans

0.14

à¤¹à¤¨

0.14

source

0.13

Zah

0.13

Activations Density 0.150%

occurrences of the preposition "in" and related contextual phrases

No Comments

No Known Activations