INDEX

Explanations

repeated mentions of practice or preparation

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

clearfix

-0.16

reb

-0.15

erm

-0.15

¶Į

-0.15

verity

-0.15

vrier

-0.14

imens

-0.14

jedn

-0.14

lectron

-0.14

POSITIVE LOGITS

antic

0.15

 sentinel

0.15

benh

0.15

-net

0.15

enic

0.15

Mec

0.15

adar

0.15

burger

0.14

bach

0.14

omic

0.14

Activations Density 0.111%

repeated mentions of practice or preparation

No Comments

No Known Activations