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 @ 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

ulu

-0.15

ãģ¦

-0.14

 Weber

-0.14

vest

-0.14

ein

-0.13

coli

-0.13

.modules

-0.13

cess

-0.13

uster

-0.13

POSITIVE LOGITS

 reform

0.17

 Reform

0.16

-divider

0.15

cntl

0.14

bou

0.14

Ball

0.14

enticated

0.14

decay

0.14

 towers

0.14

itical

0.13

Activations Density 0.030%

the preposition "in."

No Comments

No Known Activations