INDEX

Explanations

references to deputies or deputy roles in various contexts

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

cheid

-0.19

utr

-0.15

gi

-0.15

rig

-0.15

pu

-0.14

ÏģÎ¹ÏĥÏĦ

-0.14

nu

-0.14

 grav

-0.14

eder

-0.14

ulary

-0.14

POSITIVE LOGITS

_DH

0.15

íĹĮ

0.14

kich

0.14

/full

0.14

à¸Ħà¸¥

0.14

rez

0.14

pper

0.13

æīĺ

0.13

creative

0.13

Activations Density 0.007%

references to deputies or deputy roles in various contexts

No Comments

No Known Activations