INDEX

Explanations

the word "we" and its variants, indicating a focus on collective identity and togetherness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

renal

-0.15

antom

-0.14

efa

-0.14

 evidence

-0.14

ponde

-0.14

graf

-0.14

#region

-0.13

sono

-0.13

olt

-0.13

osen

-0.13

POSITIVE LOGITS

oft

0.18

deaux

0.17

ifecycle

0.14

uality

0.14

iolet

0.14

VR

0.14

LastError

0.14

igt

0.13

Merchant

0.13

umlu

0.13

Activations Density 0.278%

the word "we" and its variants, indicating a focus on collective identity and togetherness

No Comments

No Known Activations