INDEX

Explanations

references to names and how individuals are addressed in relation to their identity

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

imei

-0.15

ERC

-0.15

ars

-0.15

eliac

-0.15

Ì£

-0.14

 defaultMessage

-0.14

lab

-0.14

sko

-0.14

.lab

-0.14

 Kelley

-0.14

POSITIVE LOGITS

loe

0.17

/id

0.16

Works

0.16

ToPoint

0.15

ume

0.15

chant

0.15

enda

0.14

LN

0.14

klu

0.14

 extent

0.14

Activations Density 0.208%

references to names and how individuals are addressed in relation to their identity

No Comments

No Known Activations