INDEX

Explanations

statements that assert or emphasize factual information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

erah

-0.18

axon

-0.17

fant

-0.15

uyu

-0.15

chwitz

-0.15

Anyway

-0.15

 Anyway

-0.14

inheritDoc

-0.14

yet

-0.13

ICO

-0.13

POSITIVE LOGITS

 sogar

0.19

scratch

0.19

ually

0.17

 even

0.17

ave

0.16

arend

0.16

umber

0.16

lider

0.15

á¿¦

0.15

 sometimes

0.15

Activations Density 0.028%

statements that assert or emphasize factual information

No Comments

No Known Activations