INDEX

Explanations

recurring references to "the" in various contexts

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

hazi

-0.17

ania

-0.16

inand

-0.15

 VERY

-0.15

 Very

-0.15

ÙĩÙĨ

-0.15

 very

-0.15

.ibatis

-0.15

hatt

-0.14

åŁºæľ¬

-0.14

POSITIVE LOGITS

 anymore

0.25

 slightest

0.23

 necessarily

0.23

 same

0.23

 fault

0.20

same

0.20

 type

0.19

 sort

0.19

nor

0.19

 usual

0.19

Activations Density 0.053%

recurring references to "the" in various contexts

No Comments

No Known Activations