INDEX

Explanations

references to summaries and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Career

-0.17

RI

-0.16

duk

-0.15

 Stranger

-0.15

gi

-0.14

 Strand

-0.14

 career

-0.14

heid

-0.14

wich

-0.14

IDE

-0.14

POSITIVE LOGITS

amber

0.17

imest

0.16

isObject

0.15

_references

0.14

isArray

0.14

ouched

0.14

ognito

0.14

mpr

0.14

senal

0.14

isFunction

0.14

Activations Density 0.001%

references to summaries and organizational structures

No Comments

No Known Activations