INDEX

Explanations

phrases indicating conditional scenarios or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

cio

-0.15

rix

-0.15

 shared

-0.15

elt

-0.15

ide

-0.14

rx

-0.14

rik

-0.14

eldon

-0.14

bach

-0.13

 infl

-0.13

POSITIVE LOGITS

odyn

0.17

lesc

0.16

 available

0.15

steller

0.15

_easy

0.15

 offer

0.15

available

0.15

mpar

0.15

ToDevice

0.14

 offers

0.14

Activations Density 0.013%

phrases indicating conditional scenarios or potential outcomes

No Comments

No Known Activations