INDEX

Explanations

elements related to historical or political discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ø§ØªÙĩ

-0.14

Âł

-0.13

and

-0.13

ten

-0.13

-m

-0.13

how

-0.13

 Gone

-0.13

POSITIVE LOGITS

-Length

0.18

URLException

0.17

-Origin

0.16

-Language

0.15

styleType

0.15

likler

0.15

-Based

0.15

aeper

0.15

-REAL

0.15

PLIC

0.15

Activations Density 2.356%

elements related to historical or political discourse

No Comments

No Known Activations