INDEX

Explanations

references to governance, law, and authoritative institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ses

-0.20

/or

-0.20

tempts

-0.18

bidden

-0.17

nger

-0.16

/her

-0.15

planation

-0.15

plevel

-0.15

eyse

-0.14

ldr

-0.14

POSITIVE LOGITS

orem

0.31

notated

0.20

semble

0.18

/OR

0.18

noDB

0.17

manuel

0.17

/Branch

0.17

_FILENO

0.17

/Sub

0.16

ocene

0.16

Activations Density 0.716%

references to governance, law, and authoritative institutions

No Comments

No Known Activations