INDEX

Explanations

terms related to the concept of "as" used in various contexts for comparison or description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ucker

-0.17

enko

-0.17

andan

-0.16

ander

-0.15

urve

-0.15

grim

-0.15

Ã³n

-0.15

onte

-0.14

Bek

-0.14

ÙĦØ§ÙĨ

-0.14

POSITIVE LOGITS

«ĺ

0.16

PrototypeOf

0.16

.vn

0.15

ropoda

0.15

/stdc

0.15

 experienced

0.15

 addCriterion

0.15

 relates

0.15

AxisSize

0.15

urance

0.14

Activations Density 0.079%

terms related to the concept of "as" used in various contexts for comparison or description

No Comments

No Known Activations