INDEX

Explanations

names or terms related to individuals, places, and cultural references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 harmless

-0.15

anks

-0.14

 clickable

-0.14

clamation

-0.14

 patron

-0.14

itez

-0.14

ActiveSheet

-0.14

lane

-0.14

gov

-0.14

ftime

-0.13

POSITIVE LOGITS

uffman

0.18

aoke

0.18

akhstan

0.16

istrovstvÃŃ

0.16

ìĬ

0.16

çĪ½

0.15

Ð½Ð¾Ð·

0.15

 beden

0.15

mere

0.15

bitset

0.15

Activations Density 0.029%

names or terms related to individuals, places, and cultural references

No Comments

No Known Activations