INDEX

Explanations

conditional statements emphasizing possibilities and hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.vertx

-0.18

groupid

-0.15

tered

-0.14

DIRECTORY

-0.14

okoj

-0.14

iren

-0.14

ngÃ¶r

-0.14

ãĥĥãĥĦ

-0.14

_UNS

-0.14

#-

-0.14

POSITIVE LOGITS

acher

0.17

Urb

0.15

ibbon

0.15

anos

0.14

 Father

0.14

to

0.14

 Baxter

0.14

 Shank

0.14

min

0.14

lek

0.14

Activations Density 0.101%

conditional statements emphasizing possibilities and hypothetical scenarios

No Comments

No Known Activations