INDEX

Explanations

phrases related to access, particularly in contexts involving inequality or social services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 TRACE

-0.17

utches

-0.15

avia

-0.15

etrics

-0.15

éī

-0.15

 Trace

-0.15

amilia

-0.15

nika

-0.15

ines

-0.14

illos

-0.14

POSITIVE LOGITS

 Eden

0.19

macen

0.15

UTE

0.15

ood

0.15

Independent

0.14

ÑĢÐµÐ¹

0.14

.GetText

0.14

pag

0.14

¤

0.14

ValidationError

0.14

Activations Density 0.023%

phrases related to access, particularly in contexts involving inequality or social services

No Comments

No Known Activations