INDEX

Explanations

words related to infidelity and dishonesty, particularly in relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

numer

-0.16

Ð¾ÑĤÑĮ

-0.15

nist

-0.15

opher

-0.15

hiro

-0.15

lement

-0.15

bes

-0.14

ALI

-0.14

 occasion

-0.14

opoulos

-0.14

POSITIVE LOGITS

fully

0.20

empo

0.17

atham

0.16

yre

0.16

ê³¡

0.16

reck

0.15

.setViewport

0.15

ulous

0.15

empor

0.15

emetery

0.15

Activations Density 0.012%

words related to infidelity and dishonesty, particularly in relationships

No Comments

No Known Activations