INDEX

Explanations

negations and expressions of doubt or uncertainty in statements

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

mazon

-0.17

unas

-0.15

ijke

-0.14

Ø±ÙĪØ³

-0.14

amburg

-0.14

inet

-0.14

.ravel

-0.14

 çĤ

-0.13

Trap

-0.13

OOM

-0.13

POSITIVE LOGITS

VF

0.17

ãĤ

0.15

 powder

0.15

ey

0.14

issing

0.14

BU

0.14

rif

0.14

iÃ§

0.14

CTR

0.14

ãĤĥ

0.13

Activations Density 0.372%

negations and expressions of doubt or uncertainty in statements

No Comments

No Known Activations