INDEX

Explanations

instances of connections and relationships among various subjects or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.easing

-0.15

ÎŁÎļ

-0.14

reachable

-0.14

LIC

-0.14

adj

-0.14

ÏĢÎ·

-0.14

OMB

-0.14

erosis

-0.13

razier

-0.13

ŀ

-0.13

POSITIVE LOGITS

iner

0.16

ÏĥÏĩ

0.15

athy

0.15

Ens

0.14

asz

0.14

chan

0.14

atÄ±r

0.13

inx

0.13

çĶ°

0.13

Ð¸ÑģÐ»Ð¾Ð²

0.13

Activations Density 0.345%

instances of connections and relationships among various subjects or elements

No Comments

No Known Activations