INDEX

Explanations

dates and chronological references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rescia

-0.15

eor

-0.14

neau

-0.14

Ã¤s

-0.14

hiba

-0.14

 behalf

-0.14

esus

-0.13

sted

-0.13

hurst

-0.13

chaft

-0.13

POSITIVE LOGITS

0.25

0.20

0.17

0.16

0.15

Activations Density 0.034%

dates and chronological references

No Comments

No Known Activations