INDEX

Explanations

instances of self-reference and personal opinion expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

breadcrumbs

-0.15

 Understand

-0.15

ovich

-0.14

Å¡ak

-0.14

Ð³Ð»

-0.14

sounds

-0.14

 Ð¿Ð°Ð´

-0.14

hall

-0.14

arat

-0.13

igest

-0.13

POSITIVE LOGITS

 comparison

0.18

 recalled

0.18

 argument

0.18

 nhá»Ľ

0.17

 remembered

0.16

comparison

0.16

 Comparison

0.16

onder

0.16

 reminder

0.16

Comparison

0.16

Activations Density 0.029%

instances of self-reference and personal opinion expressions

No Comments

No Known Activations