INDEX

Explanations

words related to political discussions and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

hof

-0.17

ãĥģ

-0.15

 Barber

-0.15

py

-0.15

iek

-0.14

cap

-0.14

dbus

-0.14

etler

-0.13

/release

-0.13

POSITIVE LOGITS

wner

0.17

wer

0.16

 tÆ°á»£ng

0.15

erif

0.15

 patron

0.15

WARE

0.15

è¯Ŀ

0.15

WER

0.14

 TMPro

0.14

arl

0.14

Activations Density 0.018%

words related to political discussions and actions

No Comments

No Known Activations