INDEX

Explanations

references to language and teaching qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.scalablytyped

-0.15

ÐĲÑĢÑħÑĸÐ²

-0.15

isd

-0.14

elder

-0.14

arParams

-0.14

 ******************************************************************************↵

-0.13

undry

-0.13

VisualStyle

-0.13

sik

-0.13

ezier

-0.12

POSITIVE LOGITS

Eng

0.98

Eng

0.87

eng

0.86

ENG

0.81

ENG

0.75

-eng

0.75

 English

0.74

eng

0.74

 Engl

0.73

_eng

0.71

Activations Density 0.173%

references to language and teaching qualifications

No Comments

No Known Activations