INDEX

Explanations

Swedish words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rip

-0.15

aru

-0.15

ument

-0.15

-0.14

ordes

-0.14

anych

-0.14

elden

-0.14

 Modular

-0.14

åŁĭ

-0.14

 crisis

-0.13

POSITIVE LOGITS

Fam

0.16

ÑĢÐ°ÑģÑĤÐ°

0.14

.ie

0.14

 adverts

0.14

omanip

0.14

ÑĢÐµÑģ

0.13

-choice

0.13

Ð±Ð¾ÑĢÐ°

0.13

ille

0.13

berra

0.13

Activations Density 0.000%

Swedish words

No Comments

No Known Activations