INDEX

Explanations

references to career and educational achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

/rest

-0.21

 Ryder

-0.20

 Roma

-0.20

/render

-0.20

/reset

-0.20

 retros

-0.19

 Rash

-0.19

 Richt

-0.19

/rss

-0.19

/respond

-0.19

POSITIVE LOGITS

-re

0.91

Re

0.74

-Re

0.72

_re

0.71

RE

0.70

Re

0.69

.re

0.68

re

0.66

re

0.62

_Re

0.60

Activations Density 0.645%

references to career and educational achievements

No Comments

No Known Activations

references to career and educational achievements

No Comments

No Known Activations