INDEX

Explanations

numerals and punctuation that indicate lists or bullet points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 latter

-0.16

↵

-0.15

nt

-0.14

ika

-0.14

agi

-0.13

<br

-0.13

ore

-0.13

Â´s

-0.13

POSITIVE LOGITS

ÂłÂł

0.18

 ...↵↵↵↵

0.17

/**↵↵

0.16

 [...]↵↵

0.16

The

0.16

ÂłÂłÂłÂłÂł

0.15

iversit

0.15

ÂłÂłÂłÂłÂłÂł

0.15

.Shapes

0.15

ï¸

0.14

Activations Density 0.161%

numerals and punctuation that indicate lists or bullet points

No Comments

No Known Activations