INDEX

Explanations

occurrences of the word "och" (meaning "and" in Swedish)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eren

-0.18

ÑģÐµÐ´

-0.16

aries

-0.15

cez

-0.15

åĪ¶

-0.15

eka

-0.14

 saja

-0.14

Gos

-0.14

SetTitle

-0.14

ego

-0.14

POSITIVE LOGITS

 Manning

0.15

ibbon

0.15

isphere

0.14

INLINE

0.14

Ø¹ÙĦÙĪÙħØ§Øª

0.14

 åĴ

0.14

imat

0.14

urgeon

0.14

ë¨¸ëĭĪ

0.14

onth

0.14

Activations Density 0.007%

occurrences of the word "och" (meaning "and" in Swedish)

No Comments

No Known Activations