INDEX

Explanations

colons and associated phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

apat

-0.16

ette

-0.15

razione

-0.15

Å¾iv

-0.15

stakes

-0.15

inte

-0.14

 subsequ

-0.14

esp

-0.14

contrast

-0.14

ãĥ«ãĥķ

-0.14

POSITIVE LOGITS

0.18

ait

0.17

eko

0.16

Untitled

0.16

AIT

0.15

unt

0.15

æ¬¾

0.14

wis

0.14

parated

0.14

Activations Density 0.001%

colons and associated phrases

No Comments

No Known Activations