INDEX

Explanations

phrases associated with "ac."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

arkin

-0.17

-0.16

-0.15

TypeInfo

-0.15

-0.14

åĪĩãĤĬ

-0.14

POSITIVE LOGITS

 Quint

0.16

adr

0.15

.mac

0.15

VOKE

0.14

ilyn

0.14

.dc

0.14

indr

0.14

Ð¾Ð³

0.14

oglob

0.14

_VLAN

0.14

Activations Density 0.033%

phrases associated with "ac."

No Comments

No Known Activations