INDEX

Explanations

phrases related to searching for information about individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

¶Į

-0.16

.AI

-0.15

ANJI

-0.15

mitters

-0.15

mitter

-0.15

icks

-0.15

landers

-0.15

.ide

-0.15

ListNode

-0.14

ilib

-0.14

POSITIVE LOGITS

 Spectrum

0.17

 Jensen

0.15

gas

0.14

rar

0.14

 Crescent

0.14

ATER

0.13

 Kemp

0.13

arnings

0.13

 Chapman

0.13

ashing

0.13

Activations Density 0.004%

phrases related to searching for information about individuals

No Comments

No Known Activations