INDEX

Explanations

instances of change or shifts in power

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 perhaps

-0.18

 surely

-0.15

perhaps

-0.15

Perhaps

-0.15

utsch

-0.14

gravity

-0.14

abra

-0.14

 gravity

-0.14

opens

-0.14

.clips

-0.14

POSITIVE LOGITS

{{

0.16

 treaties

0.16

 âĹ

0.15

 Basically

0.14

nid

0.13

 Classical

0.13

 reform

0.13

 naval

0.13

 treaty

0.13

ãĤ¿ãĥ¼

0.13

Activations Density 0.000%

instances of change or shifts in power

No Comments

No Known Activations