INDEX

Explanations

terms indicating negation or exceptions to rules or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

haf

-0.15

 nonzero

-0.15

ally

-0.14

urnished

-0.14

CHO

-0.14

ÏįÎ½

-0.14

ãĤĩãģĨ

-0.14

-0.13

gable

-0.13

POSITIVE LOGITS

ĥ

0.17

 slightest

0.16

UIS

0.15

nyder

0.15

ead

0.15

 anymore

0.15

æ³¥

0.15

çĶ²

0.14

zsche

0.14

.createObject

0.14

Activations Density 0.118%

terms indicating negation or exceptions to rules or statements

No Comments

No Known Activations