INDEX

Explanations

expressions of confusion or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

eus

-0.16

FXML

-0.15

atto

-0.15

uries

-0.15

.ml

-0.15

rÅ¾

-0.14

hay

-0.13

Const

-0.13

oÄŁ

-0.13

hal

-0.13

POSITIVE LOGITS

/feed

0.15

 rent

0.15

ike

0.15

span

0.14

aldi

0.14

atham

0.14

olist

0.14

ANGO

0.13

etsk

0.13

annah

0.13

Activations Density 0.032%

expressions of confusion or uncertainty

No Comments

No Known Activations