INDEX

Explanations

numeric values and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oyer

-0.17

ãĥ³ãĥĩ

-0.16

ÙħØ³

-0.15

oso

-0.15

contri

-0.15

ATUS

-0.15

_glob

-0.14

èī

-0.14

pd

-0.14

 Glob

-0.14

POSITIVE LOGITS

 mans

0.16

elyn

0.15

ilename

0.15

Disposed

0.14

adin

0.14

 enjo

0.14

æķ£

0.14

andler

0.13

andise

0.13

uben

0.13

Activations Density 0.064%

numeric values and their associated contexts

No Comments

No Known Activations