INDEX

Explanations

the term "retired" or related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ba

-0.17

awi

-0.16

unker

-0.16

ova

-0.15

itan

-0.14

 principle

-0.14

Sud

-0.14

Cav

-0.14

yl

-0.13

alam

-0.13

POSITIVE LOGITS

tainment

0.18

ATES

0.15

ãĥ¡ãĥ³ãĥĪ

0.15

ÑħÐ¾Ð²

0.14

 modelName

0.14

åŃĺäºİ

0.14

actus

0.14

dbh

0.14

ogui

0.14

 Ð°Ð´Ð¶Ðµ

0.14

Activations Density 0.009%

the term "retired" or related variations

No Comments

No Known Activations