INDEX

Explanations

information about notable organizations and their prominence in various industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.16

reck

-0.15

-0.14

esian

-0.14

onte

-0.14

ione

-0.13

ĵĺ

-0.13

POSITIVE LOGITS

quoise

0.16

'gc

0.16

 provider

0.15

racat

0.15

 providers

0.15

providers

0.15

 poskyt

0.15

 numberWith

0.14

ardash

0.14

provider

0.14

Activations Density 0.080%

information about notable organizations and their prominence in various industries

No Comments

No Known Activations