INDEX

Explanations

phrases that indicate reference to prior statements or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

acho

-0.17

 Carn

-0.16

 negatives

-0.15

 Progressive

-0.14

 ØŃØ§Ø¬

-0.14

oge

-0.14

acades

-0.14

ires

-0.14

otte

-0.14

at

-0.14

POSITIVE LOGITS

imdi

0.16

 kolo

0.16

pend

0.15

pig

0.15

.Entry

0.15

">//

0.14

cÃ¼

0.14

uzzi

0.14

rvine

0.14

yasal

0.14

Activations Density 0.063%

phrases that indicate reference to prior statements or discussions

No Comments

No Known Activations