INDEX

Explanations

phrases that refer to "go-to" options or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ullo

-0.18

usement

-0.15

riel

-0.15

echa

-0.15

ablo

-0.14

ardin

-0.14

kte

-0.14

 chim

-0.14

aler

-0.14

 Stern

-0.14

POSITIVE LOGITS

ÑĢÐµÑĪ

0.15

 norge

0.15

istrovstvÃŃ

0.15

obox

0.15

ffffffff

0.14

ernen

0.14

(predicate

0.14

ivet

0.14

_DIRECT

0.14

Activations Density 0.005%

phrases that refer to "go-to" options or recommendations

No Comments

No Known Activations