INDEX

Explanations

references to data points, statistics, and measurable outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ISMATCH

-0.16

 andre

-0.14

arden

-0.14

MPU

-0.14

Î³ÏģÎ±

-0.13

iske

-0.13

ammer

-0.13

aho

-0.13

organ

-0.12

annis

-0.12

POSITIVE LOGITS

 cock

0.16

esome

0.15

cock

0.14

 Rice

0.14

erb

0.14

emos

0.14

 Cock

0.13

edo

0.13

hone

0.13

sez

0.13

Activations Density 2.464%

references to data points, statistics, and measurable outcomes

No Comments

No Known Activations