INDEX

Explanations

instances of the word "recently" to identify discussions or updates about recent events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð´ÐµÑĤ

-0.15

ertas

-0.14

 record

-0.14

axes

-0.14

rippling

-0.14

resh

-0.13

ungal

-0.13

records

-0.13

ÙĦØ§ÙĦ

-0.13

pc

-0.13

POSITIVE LOGITS

eler

0.15

achten

0.14

ãĥĥãĥĦ

0.14

alous

0.14

ame

0.14

mente

0.14

stellung

0.14

éĿ

0.14

/pop

0.13

.codes

0.13

Activations Density 0.032%

instances of the word "recently" to identify discussions or updates about recent events or occurrences

No Comments

No Known Activations