INDEX

Explanations

phrases related to the fitting or installation of objects or systems

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

sted

-0.17

éŀ

-0.15

els

-0.15

ç¥¨

-0.15

ansen

-0.14

ÏĪÎ·

-0.14

ffield

-0.14

onen

-0.14

atee

-0.14

POSITIVE LOGITS

TURE

0.16

ìĭľëĬĶ

0.15

oggler

0.15

mach

0.15

Addon

0.15

ãĥ©ãĥ¼

0.15

ting

0.15

ternet

0.14

-urlencoded

0.14

omal

0.14

Activations Density 0.023%

phrases related to the fitting or installation of objects or systems

No Comments

No Known Activations