INDEX

Explanations

references to significant actions or events within a narrative context

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

Î¸ÎŃ

-0.15

 ÙħØŃ

-0.14

ldr

-0.14

çĸĨ

-0.14

werk

-0.14

lict

-0.13

lett

-0.13

linger

-0.13

èĮĥ

-0.13

bins

-0.13

POSITIVE LOGITS

ekler

0.16

ACE

0.16

 details

0.15

CD

0.15

otec

0.15

 Bilim

0.14

detail

0.14

Ace

0.14

adaki

0.14

 branches

0.14

Activations Density 0.001%

references to significant actions or events within a narrative context

No Comments

No Known Activations