INDEX

Explanations

mentions of specific U.S. states and their relevance within the context of government, policy, or local issues

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elder

-0.16

Ì£

-0.16

eka

-0.16

ackbar

-0.15

enza

-0.14

 Bakan

-0.14

egt

-0.14

tÃ©

-0.13

uler

-0.13

POSITIVE LOGITS

-wide

0.27

-specific

0.20

wide

0.19

ians

0.17

(ns

0.16

 unique

0.15

 wide

0.15

plc

0.14

unique

0.14

aa

0.14

Activations Density 0.247%

mentions of specific U.S. states and their relevance within the context of government, policy, or local issues

No Comments

No Known Activations