INDEX

Explanations

elements related to climbing or mountainous terrain

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Mountains

-0.17

 hills

-0.16

 mountain

-0.16

 muddy

-0.15

 Mountain

-0.15

 mountains

-0.15

 Pier

-0.15

 Hill

-0.15

-0.14

 hill

-0.14

POSITIVE LOGITS

 bomber

0.17

Exposed

0.17

 traverse

0.16

ruz

0.15

notated

0.15

elters

0.15

anik

0.15

nels

0.15

.easy

0.14

ehler

0.14

Activations Density 0.013%

elements related to climbing or mountainous terrain

No Comments

No Known Activations