INDEX

Explanations

terms that indicate causation or consequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

arus

-0.17

lar

-0.16

sg

-0.14

ril

-0.14

PF

-0.13

lover

-0.13

Ã¼l

-0.13

inou

-0.13

raries

-0.13

POSITIVE LOGITS

forth

0.21

aze

0.15

 confront

0.15

ÙĪØ§Ø±

0.15

unt

0.14

eme

0.14

acer

0.14

ays

0.14

 detr

0.14

Activations Density 0.006%

terms that indicate causation or consequence

No Comments

No Known Activations