INDEX

Explanations

phrases that indicate an evaluation or comparison of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

veau

-0.15

chy

-0.15

vic

-0.15

ValueCollection

-0.14

ookie

-0.14

elin

-0.14

atan

-0.13

ech

-0.13

ton

-0.13

POSITIVE LOGITS

erk

0.18

Explorer

0.15

assis

0.15

UPDATED

0.15

¢åįķ

0.14

etu

0.14

[text

0.14

mez

0.14

orderby

0.14

azz

0.14

Activations Density 0.010%

phrases that indicate an evaluation or comparison of items

No Comments

No Known Activations