INDEX

Explanations

references to a specific individual named Shah

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

terminal

-0.16

 Vern

-0.15

seat

-0.14

ãĤ¿ãĥ³

-0.14

 rooting

-0.14

inv

-0.14

etus

-0.13

atories

-0.13

coat

-0.13

 extremes

-0.13

POSITIVE LOGITS

baz

0.19

erve

0.17

iÃŃ

0.16

unist

0.16

eneg

0.16

_backward

0.15

eniz

0.15

olar

0.15

0.14

peare

0.14

Activations Density 0.028%

references to a specific individual named Shah

No Comments

No Known Activations