INDEX

Explanations

phrases indicating actions or intentions, particularly those starting with "to."

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

ovah

-0.16

uchs

-0.16

raya

-0.16

otate

-0.16

loys

-0.15

oland

-0.15

asons

-0.15

&uuml

-0.15

ouden

-0.15

ctica

-0.14

POSITIVE LOGITS

kol

0.14

ÄħÅ¼

0.14

ustr

0.14

 Brewer

0.14

arsi

0.13

rot

0.13

Flo

0.13

Crow

0.13

angu

0.13

Activations Density 0.039%

phrases indicating actions or intentions, particularly those starting with "to."

No Comments

No Known Activations