INDEX

Explanations

significant actions or events related to attendance or participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

imer

-0.15

ovol

-0.14

áº¥p

-0.14

rst

-0.14

wire

-0.14

ubre

-0.14

à¹ĩà¸Ķ

-0.13

 Heidi

-0.13

endra

-0.13

 Religious

-0.13

POSITIVE LOGITS

:convert

0.16

rop

0.16

swick

0.15

spiracy

0.15

omat

0.14

allas

0.14

ÙħØ§Ø±

0.14

iyim

0.14

enheim

0.14

brick

0.14

Activations Density 0.039%

significant actions or events related to attendance or participation

No Comments

No Known Activations