INDEX

Explanations

phrases indicating significant events or changes, particularly pertaining to the emergence or introduction of new concepts or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

AAAA

-0.14

ldr

-0.14

naÄį

-0.14

iteur

-0.14

estate

-0.14

intl

-0.13

stras

-0.13

³

-0.13

pcb

-0.13

Î³Î¼Î±

-0.13

POSITIVE LOGITS

éŁ¿

0.14

0.13

cores

0.13

äºķ

0.13

fad

0.13

Activations Density 0.089%

phrases indicating significant events or changes, particularly pertaining to the emergence or introduction of new concepts or phenomena

No Comments

No Known Activations