INDEX

Explanations

the presence of specific words or phrases related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

icast

-0.16

rosse

-0.16

elix

-0.15

YSTEM

-0.15

ells

-0.15

hus

-0.15

lix

-0.15

ICAST

-0.15

ÑĥÐ¶Ð´

-0.15

ostream

-0.14

POSITIVE LOGITS

Ham

0.19

ham

0.18

 craft

0.17

 Craft

0.17

Craft

0.17

HAM

0.16

 Southampton

0.16

Ham

0.16

craft

0.15

Gre

0.15

Activations Density 0.034%

the presence of specific words or phrases related to authority and governance

No Comments

No Known Activations