INDEX

Explanations

phrases indicating a lack of recognition or understanding

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

_PUS

-0.17

ching

-0.14

uci

-0.14

erty

-0.14

ãģıãģł

-0.14

angible

-0.14

vard

-0.14

erna

-0.14

emas

-0.14

 Ð¶Ðµ

-0.14

POSITIVE LOGITS

neath

0.28

sea

0.18

lrt

0.17

ling

0.17

lings

0.17

whelming

0.17

NR

0.16

halb

0.15

whel

0.15

ijkstra

0.15

Activations Density 0.088%

phrases indicating a lack of recognition or understanding

No Comments

No Known Activations