INDEX

Explanations

terms related to land and water environments, especially their function in military or combat contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 loose

-0.16

 Loose

-0.16

ÑĥÐ´Ð°

-0.14

etty

-0.14

uby

-0.14

Ð¾ÑĢÐµ

-0.14

ä»½

-0.14

Ã©al

-0.14

owie

-0.13

rah

-0.13

POSITIVE LOGITS

anchor

0.16

hoff

0.15

isch

0.14

eller

0.14

mej

0.14

 anchor

0.14

signature

0.14

valid

0.14

 blocks

0.14

xb

0.14

Activations Density 0.051%

terms related to land and water environments, especially their function in military or combat contexts

No Comments

No Known Activations