INDEX

Explanations

variations of the word "leak" and related terms

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

egie

-0.16

anine

-0.15

aket

-0.14

atoi

-0.14

iene

-0.13

ena

-0.13

 chained

-0.13

ç¹ģ

-0.13

Ð¾Ð»Ð¾

-0.13

ows

-0.13

POSITIVE LOGITS

alic

0.16

ureau

0.16

cljs

0.15

ermann

0.14

ext

0.14

beck

0.14

cpy

0.14

ãĥªãĤ«

0.14

 Ð¿Ð¾Ñħ

0.14

cir

0.13

Activations Density 0.010%

variations of the word "leak" and related terms

No Comments

No Known Activations