INDEX

Explanations

research-related terminology and phrases indicative of investigation and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antine

-0.17

ìĹ

-0.16

oot

-0.15

lom

-0.15

Wa

-0.14

chter

-0.14

ooke

-0.14

anoia

-0.14

POSITIVE LOGITS

çŃĭ

0.16

 sÄ±ras

0.15

DSA

0.14

jong

0.14

 Desire

0.14

 Ð½Ð°Ð½ÐµÑģ

0.14

>>::

0.13

 cast

0.13

CLUD

0.13

agedList

0.13

Activations Density 0.137%

research-related terminology and phrases indicative of investigation and analysis

No Comments

No Known Activations