INDEX

Explanations

occurrences of the letter 'I' in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kle

-0.15

Ä©nh

-0.15

 Amerikan

-0.14

icc

-0.14

Ã´le

-0.14

ekim

-0.14

 neut

-0.14

kle

-0.14

 Closet

-0.14

POSITIVE LOGITS

riangle

0.16

Î´Î¿ÏĤ

0.15

Ð°Ð´ÐºÐ¸

0.14

/features

0.14

issors

0.14

à¤¾à¤¹à¤¤

0.14

ivariate

0.13

anuts

0.13

_escape

0.13

enced

0.13

Activations Density 0.062%

occurrences of the letter 'I' in various forms

No Comments

No Known Activations