INDEX

Explanations

conditional statements involving logical operators and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Peters

-0.16

ioni

-0.15

entai

-0.15

 uncomment

-0.15

patial

-0.15

acking

-0.15

èĵ

-0.14

ubb

-0.14

ervas

-0.14

precated

-0.14

POSITIVE LOGITS

PIPE

0.16

racak

0.15

ÐĽÐ¬

0.15

ibi

0.15

çº

0.14

ffen

0.14

 Singer

0.14

aggio

0.14

IFA

0.14

omnia

0.13

Activations Density 0.128%

conditional statements involving logical operators and values

No Comments

No Known Activations