INDEX

Explanations

phrases indicating a return or coming back to a previous state or place

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

onus

-0.17

edis

-0.16

oyer

-0.16

ottes

-0.15

umpt

-0.15

aptors

-0.14

inue

-0.14

egin

-0.14

 Prairie

-0.14

edly

-0.13

POSITIVE LOGITS

upp

0.16

Ð°Ð»Ð¾

0.15

Naz

0.14

Naz

0.14

exampleInputEmail

0.14

 centre

0.14

Ã¤nge

0.13

Timing

0.13

razier

0.13

pline

0.13

Activations Density 0.014%

phrases indicating a return or coming back to a previous state or place

No Comments

No Known Activations