INDEX

Explanations

expressions of dissatisfaction or negative emotions

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

asca

-0.16

ascar

-0.16

ousse

-0.15

frei

-0.15

ModelState

-0.14

cum

-0.14

palette

-0.14

upro

-0.14

 Benefit

-0.13

OfType

-0.13

POSITIVE LOGITS

indle

0.15

izr

0.15

iz

0.14

aliz

0.14

ll

0.14

ocale

0.14

agy

0.14

ched

0.14

Contin

0.13

hal

0.13

Activations Density 0.003%

expressions of dissatisfaction or negative emotions

No Comments

No Known Activations

expressions of dissatisfaction or negative emotions

No Comments

No Known Activations