INDEX

Explanations

terms related to identity or categorization in a particular context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ivid

-0.19

vala

-0.14

ulent

-0.14

 paran

-0.14

uele

-0.14

emode

-0.14

inery

-0.14

otine

-0.14

Ø±Ø§

-0.14

Serialized

-0.14

POSITIVE LOGITS

igkeit

0.17

icari

0.16

loy

0.15

 Berm

0.14

 stron

0.14

defer

0.14

 Insider

0.14

izzo

0.14

quier

0.14

æĪ

0.13

Activations Density 0.047%

terms related to identity or categorization in a particular context

No Comments

No Known Activations