INDEX

Explanations

conditional phrases and hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.scalablytyped

-0.21

abcdefghijkl

-0.15

.Aggressive

-0.15

 Sanayi

-0.15

FindObject

-0.15

actionDate

-0.14

Ð¾Ð´Ð¾

-0.14

otionEvent

-0.14

hdl

-0.14

odem

-0.14

POSITIVE LOGITS

0.15

agara

0.15

 Brand

0.14

ed

0.14

unm

0.14

 Baker

0.14

toi

0.14

lui

0.13

 apart

0.13

Activations Density 0.300%

conditional phrases and hypothetical scenarios

No Comments

No Known Activations