INDEX

Explanations

phrases related to barriers and obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

allet

-0.15

SCAN

-0.15

asket

-0.14

isd

-0.14

venes

-0.14

iske

-0.13

åľŃ

-0.13

onth

-0.13

å£

-0.13

 Horton

-0.13

POSITIVE LOGITS

ikal

0.15

/bar

0.15

 imped

0.15

 barriers

0.15

/block

0.15

0.14

 obstacles

0.14

:block

0.14

Activations Density 0.066%

phrases related to barriers and obstacles

No Comments

No Known Activations