INDEX

Explanations

terms related to transformation or change, particularly in a geographical or narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

acom

-0.15

 kenn

-0.15

eza

-0.14

rlen

-0.14

ahoma

-0.14

enny

-0.14

mando

-0.14

ignKey

-0.13

reed

-0.13

 welt

-0.13

POSITIVE LOGITS

 secs

0.20

 gross

0.20

gross

0.18

sec

0.16

bl

0.16

 suspend

0.16

 fossil

0.15

iesel

0.15

 odor

0.15

 adam

0.15

Activations Density 0.123%

terms related to transformation or change, particularly in a geographical or narrative context

No Comments

No Known Activations