INDEX

Explanations

mentions of a specific individual, highlighting a prominent person's name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

æĹıèĩªæ²»

-0.17

afone

-0.16

_NT

-0.15

unca

-0.15

ning

-0.15

="__

-0.15

ervo

-0.15

-0.14

Peripheral

-0.14

ware

-0.14

POSITIVE LOGITS

lear

0.18

.codes

0.16

abad

0.15

ÄįÃŃ

0.15

TA

0.14

lob

0.14

owitz

0.14

-archive

0.14

abbage

0.14

eko

0.13

Activations Density 0.039%

mentions of a specific individual, highlighting a prominent person's name

No Comments

No Known Activations