INDEX

Explanations

expressions of personal life experiences and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Alone

-0.16

alone

-0.15

arez

-0.14

 alone

-0.14

alon

-0.14

 Exclusive

-0.14

riend

-0.14

 prelim

-0.13

ispers

-0.13

aisy

-0.13

POSITIVE LOGITS

 disproportionate

0.16

 caffe

0.16

 ridiculous

0.16

 embarrass

0.16

 whichever

0.15

 wherever

0.15

 whenever

0.15

_attempt

0.15

å°

0.15

.idea

0.15

Activations Density 0.178%

expressions of personal life experiences and connections

No Comments

No Known Activations