INDEX

Explanations

occurrences of specific URL patterns or segments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

prites

-0.17

reur

-0.15

ãĤ¯ãĥĪ

-0.15

Ø±Ø¶

-0.15

ogenerated

-0.14

æ²»

-0.14

obuf

-0.14

ãĥ³ãĥĦ

-0.14

utow

-0.14

 Hubbard

-0.14

POSITIVE LOGITS

atab

0.17

anche

0.15

Ã©ri

0.15

ä¹ĥ

0.15

otron

0.14

hee

0.14

anch

0.14

 Sidney

0.14

ANCH

0.14

ylene

0.14

Activations Density 0.028%

occurrences of specific URL patterns or segments

No Comments

No Known Activations