INDEX

Explanations

phrases that include the word "that" and its variations to identify clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acco

-0.17

acci

-0.16

.ro

-0.15

thal

-0.15

ocale

-0.15

jak

-0.15

ÐµÑĢÐ¾Ð¼

-0.15

hod

-0.15

lue

-0.15

tru

-0.15

POSITIVE LOGITS

anj

0.15

&page

0.14

Ð¾Ð»Ð¾Ð²

0.14

ombo

0.14

ify

0.14

 subt

0.14

.INSTANCE

0.14

Activations Density 0.237%

phrases that include the word "that" and its variations to identify clauses

No Comments

No Known Activations