INDEX

Explanations

negations or phrases expressing disagreement or denial

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

ezier

-0.16

 nackte

-0.16

.scalablytyped

-0.16

vÄĽt

-0.16

-0.15

rale

-0.15

ADING

-0.14

soles

-0.14

onents

-0.14

ityEngine

-0.14

POSITIVE LOGITS

 anymore

0.21

iced

0.19

icing

0.18

 necessarily

0.18

 sure

0.16

withstanding

0.16

 unless

0.15

tingham

0.15

 Sure

0.15

ingham

0.15

Activations Density 0.041%

negations or phrases expressing disagreement or denial

No Comments

No Known Activations