INDEX

Explanations

expressions of comparison and similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

autoload

-0.15

ASTER

-0.15

AIT

-0.15

interop

-0.14

olor

-0.14

 expert

-0.14

PERT

-0.13

 extr

-0.13

.FontStyle

-0.13

 doma

-0.13

POSITIVE LOGITS

deaux

0.18

 exactly

0.15

aims

0.14

geois

0.14

 ConfigureServices

0.14

èĥĨ

0.14

oup

0.14

oni

0.14

itten

0.14

 identical

0.14

Activations Density 0.370%

expressions of comparison and similarity

No Comments

No Known Activations