INDEX

Explanations

the preposition "in"

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

abler

-0.16

ushman

-0.15

aub

-0.15

ivre

-0.14

Ã´i

-0.14

akespeare

-0.14

edin

-0.14

Ã³ln

-0.14

.framework

-0.13

POSITIVE LOGITS

ostat

0.17

spl

0.16

IGHL

0.15

 sple

0.15

longleftrightarrow

0.14

à¸¢à¸¡

0.14

rial

0.14

cyan

0.14

rig

0.14

oodoo

0.13

Activations Density 0.095%

the preposition "in"

No Comments

No Known Activations