INDEX

Explanations

references to assessment tools and measurement criteria

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

æ´ĭ

-0.17

hil

-0.15

 proof

-0.15

 Proof

-0.15

å½¹

-0.14

chts

-0.14

/mac

-0.14

 laid

-0.14

abit

-0.14

cur

-0.14

POSITIVE LOGITS

ebek

0.17

Sexy

0.15

eld

0.15

ivative

0.15

ÙĪØº

0.14

upakan

0.14

elden

0.14

aper

0.14

erate

0.14

esi

0.14

Activations Density 0.027%

references to assessment tools and measurement criteria

No Comments

No Known Activations