INDEX

Explanations

words and phrases related to validity and legitimacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ires

-0.18

alc

-0.17

 Rapids

-0.15

ef

-0.15

aire

-0.15

laps

-0.14

tps

-0.14

CAA

-0.14

iel

-0.14

eil

-0.14

POSITIVE LOGITS

atable

0.25

adera

0.17

.Valid

0.16

CastException

0.16

enticator

0.15

ated

0.15

.valid

0.15

entic

0.15

(valid

0.15

vet

0.15

Activations Density 0.043%

words and phrases related to validity and legitimacy

No Comments

No Known Activations