INDEX

Explanations

specific phrases often beginning with "of" and "and," indicative of a structured, list-like format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Ð¶Ðµ

-0.14

pread

-0.14

/or

-0.14

ses

-0.14

.dtp

-0.14

dep

-0.14

peare

-0.13

prop

-0.13

AMAGE

-0.13

ÏĦÎµÏį

-0.13

POSITIVE LOGITS

obia

0.15

okt

0.15

notated

0.14

ecd

0.14

fts

0.14

apiro

0.14

@js

0.13

ãĤ¤ãĤº

0.13

anÃ©

0.13

dzi

0.13

Activations Density 0.114%

specific phrases often beginning with "of" and "and," indicative of a structured, list-like format

No Comments

No Known Activations