INDEX

Explanations

instances of the word "compared" and its variations, indicating a focus on comparative analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

iones

-0.18

.TryParse

-0.18

upo

-0.15

eric

-0.15

oser

-0.14

ayah

-0.14

Void

-0.14

sam

-0.14

utsche

-0.14

oba

-0.13

POSITIVE LOGITS

 Cruc

0.16

ogg

0.14

 Contrast

0.14

ufs

0.14

shint

0.14

Cra

0.14

0.13

gli

0.13

æĸ¼

0.13

Activations Density 0.014%

instances of the word "compared" and its variations, indicating a focus on comparative analysis

No Comments

No Known Activations