INDEX

Explanations

complex words or phrases that indicate deep emotional or philosophical themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

onga

-0.16

ÑĸÐ½ÑĮ

-0.16

CLUD

-0.14

imir

-0.14

isp

-0.14

 Codes

-0.14

codegen

-0.14

éĲĺ

-0.14

eni

-0.13

 Crawford

-0.13

POSITIVE LOGITS

0.14

umpt

0.14

TI

0.14

eson

0.14

TI

0.13

osterone

0.13

enor

0.13

âĳł

0.13

aternity

0.13

Ti

0.13

Activations Density 0.351%

complex words or phrases that indicate deep emotional or philosophical themes

No Comments

No Known Activations